def main():
align = align_dlib.AlignDlib(os.path.expanduser(FLAGS.dlib_face_predictor))
landmarkIndices = align_dlib.AlignDlib.OUTER_EYES_AND_NOSE
dataset = facenet.get_dataset(FLAGS.input_dir)
# Scale the image such that the face fills the frame when cropped to crop_size
scale = float(FLAGS.face_size) / FLAGS.image_size
for cls in dataset:
output_class_dir = os.path.join(os.path.expanduser(FLAGS.output_dir), cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
for image_path in cls.image_paths:
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir, filename+'.png')
if not os.path.exists(output_filename):
print(image_path)
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim == 2:
img = facenet.to_rgb(img)
if FLAGS.use_new_alignment:
aligned = align.align_new(FLAGS.image_size, img, landmarkIndices=landmarkIndices,
skipMulti=True, scale=scale)
else:
aligned = align.align(FLAGS.image_size, img, landmarkIndices=landmarkIndices,
skipMulti=True, scale=scale)
if aligned is not None:
misc.imsave(output_filename, aligned)
def main(args):
train_set = facenet.get_dataset(args.data_dir)
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
label_strings = [name for name in os.listdir(os.path.expanduser(args.data_dir)) if os.path.isdir(os.path.join(os.path.expanduser(args.data_dir), name))]
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
facenet.load_model(args.model_dir)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
# Run forward pass to calculate embeddings
nrof_images = len(image_list)
print('Number of images: ', nrof_images)
batch_size = args.image_batch
if nrof_images % batch_size == 0:
nrof_batches = nrof_images // batch_size
else:
nrof_batches = (nrof_images // batch_size) + 1
print('Number of batches: ', nrof_batches)
embedding_size = embeddings.get_shape()[1]
emb_array = np.zeros((nrof_images, embedding_size))
start_time = time.time()
for i in range(nrof_batches):
if i == nrof_batches -1:
n = nrof_images
else:
n = i*batch_size + batch_size
# Get images for the batch
if args.is_aligned is True:
images = facenet.load_data(image_list[i*batch_size:n], False, False, args.image_size)
else:
images = load_and_align_data(image_list[i*batch_size:n], args.image_size, args.margin, args.gpu_memory_fraction)
feed_dict = { images_placeholder: images, phase_train_placeholder:False }
# Use the facenet model to calcualte embeddings
embed = sess.run(embeddings, feed_dict=feed_dict)
emb_array[i*batch_size:n, :] = embed
print('Completed batch', i+1, 'of', nrof_batches)
run_time = time.time() - start_time
print('Run time: ', run_time)
# export emedings and labels
label_list = np.array(label_list)
np.save(args.embeddings_name, emb_array)
np.save(args.labels_name, label_list)
np.save(args.labels_strings_name, label_strings)
def main(args):
funnel_cmd = 'funnelReal'
funnel_model = 'people.train'
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the output directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
dataset = facenet.get_dataset(args.input_dir)
np.random.shuffle(dataset)
# Scale the image such that the face fills the frame when cropped to crop_size
#scale = float(args.face_size) / args.image_size
with TemporaryDirectory() as tmp_dir:
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
tmp_output_class_dir = os.path.join(tmp_dir, cls.name)
if not os.path.exists(output_class_dir) and not os.path.exists(tmp_output_class_dir):
print('Aligning class %s:' % cls.name)
tmp_filenames = []
if not os.path.exists(tmp_output_class_dir):
os.makedirs(tmp_output_class_dir)
input_list_filename = os.path.join(tmp_dir, 'input_list.txt')
output_list_filename = os.path.join(tmp_dir, 'output_list.txt')
input_file = open(input_list_filename, 'w')
output_file = open(output_list_filename,'w')
for image_path in cls.image_paths:
filename = os.path.split(image_path)[1]
input_file.write(image_path+'\n')
output_filename = os.path.join(tmp_output_class_dir, filename)
output_file.write(output_filename+'\n')
tmp_filenames.append(output_filename)
input_file.close()
output_file.close()
cmd = args.funnel_dir+funnel_cmd + ' ' + input_list_filename + ' ' + args.funnel_dir+funnel_model + ' ' + output_list_filename
subprocess.call(cmd, shell=True)
# Resize and crop images
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
scale = 1.0
for tmp_filename in tmp_filenames:
img = misc.imread(tmp_filename)
img_scale = misc.imresize(img, scale)
sz1 = img.shape[1]/2
sz2 = args.image_size/2
img_crop = img_scale[int(sz1-sz2):int(sz1+sz2),int(sz1-sz2):int(sz1+sz2),:]
filename = os.path.splitext(os.path.split(tmp_filename)[1])[0]
output_filename = os.path.join(output_class_dir, filename+'.png')
print('Saving image %s' % output_filename)
misc.imsave(output_filename, img_crop)
# Remove tmp directory with images
shutil.rmtree(tmp_output_class_dir)
def main(args):
dataset = facenet.get_dataset(args.dir)
paths, _ = facenet.get_image_paths_and_labels(dataset)
t = np.zeros((len(paths)))
x = time.time()
for i, path in enumerate(paths):
start_time = time.time()
with open(path, mode='rb') as f:
_ = f.read()
duration = time.time() - start_time
t[i] = duration
if i % 1000 == 0 or i==len(paths)-1:
print('File %d/%d Total time: %.2f Avg: %.3f Std: %.3f' % (i, len(paths), time.time()-x, np.mean(t[0:i])*1000, np.std(t[0:i])*1000))
def main():
image_size = 96
old_dataset = '/home/david/datasets/facescrub/fs_aligned_new_oean/'
new_dataset = '/home/david/datasets/facescrub/facescrub_110_96/'
eq = 0
num = 0
l = []
dataset = facenet.get_dataset(old_dataset)
for cls in dataset:
new_class_dir = os.path.join(new_dataset, cls.name)
for image_path in cls.image_paths:
try:
filename = os.path.splitext(os.path.split(image_path)[1])[0]
new_filename = os.path.join(new_class_dir, filename+'.png')
#print(image_path)
if os.path.exists(new_filename):
a = facenet.load_data([image_path, new_filename], False, False, image_size, do_prewhiten=False)
if np.array_equal(a[0], a[1]):
eq+=1
num+=1
err = np.sum(np.square(np.subtract(a[0], a[1])))
#print(err)
l.append(err)
if err>2000:
fig = plt.figure(1)
p1 = fig.add_subplot(121)
p1.imshow(a[0])
p2 = fig.add_subplot(122)
p2.imshow(a[1])
print('%6.1f: %s\n' % (err, new_filename))
pass
else:
pass
#print('File not found: %s' % new_filename)
except:
pass
def classify(src, dir):
with tf.Graph().as_default():
with tf.Session() as sess:
datadir = src
dataset = facenet.get_dataset(datadir)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
print('Loading feature extraction model')
modeldir = '20180408-102900/20180408-102900.pb'
facenet.load_model(modeldir)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
batch_size = 1000
image_size = 160
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * batch_size
end_index = min((i + 1) * batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename = dir
classifier_filename_exp = os.path.expanduser(classifier_filename)
# Train classifier
print('Training classifier')
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
print(class_names)
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
print('Goodluck')
def main(args):
logging.info('###### all args #####: %s' % args)
network = importlib.import_module(args.model_def)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Store some git revision info in a text file in the log directory
if not args.no_store_revision_info:
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
random.seed(args.seed)
train_set = facenet.get_dataset(args.data_dir)
if args.filter_filename:
train_set = filter_dataset(train_set, args.filter_filename,
args.filter_percentile, args.filter_min_nrof_images_per_class)
nrof_classes = len(train_set)
logging.info('Model directory: %s' % model_dir)
logging.info('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
logging.info('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
logging.info('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list)>0, 'The dataset should not be empty'
logging.info('image_list size %d, label_list size %d' %(len(image_list), len(label_list)))
# Create a queue that produces indices into the image_list and label_list
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
logging.info('labels shape %s, range size: %s' % (labels.shape, str(range_size)))
index_queue = tf.train.range_input_producer(range_size, num_epochs=None,
shuffle=True, seed=None, capacity=32)
logging.info('batch size:%d, epoch size:%d' % (args.batch_size ,args.epoch_size))
index_dequeue_op = index_queue.dequeue_many(args.batch_size*args.epoch_size, 'index_dequeue')
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,1), name='image_paths')
labels_placeholder = tf.placeholder(tf.int64, shape=(None,1), name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(1,), (1,)],
shared_name=None, name=None)
enqueue_op = input_queue.enqueue_many([image_paths_placeholder, labels_placeholder], name='enqueue_op')
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
logging.info('# filenames len:%s' % filenames.shape)
images = []
for filename in tf.unstack(filenames):
# logging.info('#file:%s' % filename)
file_contents = tf.read_file(filename)
image = tf.image.decode_jpeg(file_contents)
logging.info('#image shape:%s' % image.shape)
if args.random_rotate:
image = tf.py_func(facenet.random_rotate_image, [image], tf.uint8)
# if args.random_crop:
# image = tf.random_crop(image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
image_batch, label_batch = tf.train.batch_join(
images_and_labels, batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()], enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
label_batch = tf.identity(label_batch, 'label_batch')
logging.info('Total number of classes: %d' % nrof_classes)
logging.info('Total number of examples: %d' % len(image_list))
logging.info('Building training graph')
batch_norm_params = {
# Decay for the moving averages
'decay': 0.995,
# epsilon to prevent 0s in variance
'epsilon': 0.001,
# force in-place updates of mean and variance estimates
'updates_collections': None,
# Moving averages ends up in the trainable variables collection
'variables_collections': [ tf.GraphKeys.TRAINABLE_VARIABLES ],
# Only update statistics during training mode
'is_training': phase_train_placeholder
}
# Build the inference graph
# with tf.device('/GPU:0'):
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, weight_decay=args.weight_decay)
bottleneck = slim.fully_connected(prelogits, args.embedding_size, activation_fn=None,
weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params,
scope='Bottleneck', reuse=False)
logits = slim.fully_connected(bottleneck, len(train_set), activation_fn=None,
weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits', reuse=False)
embeddings = tf.nn.l2_normalize(bottleneck, 1, 1e-10, name='embeddings')
# Add center loss
if args.center_loss_factor>0.0:
prelogits_center_loss, _ = facenet.center_loss(prelogits, label_batch, args.center_loss_alfa, nrof_classes)
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch, logits=logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, tf.global_variables(), args.log_histograms)
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=10)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default() , tf.device('/gpu:1'):
if pretrained_model:
logging.info('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
logging.info('Running training')
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, epoch, image_list, label_list, index_dequeue_op, enqueue_op, image_paths_placeholder, labels_placeholder,
learning_rate_placeholder, phase_train_placeholder, batch_size_placeholder, global_step,
total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step)
# Evaluate on LFW
if args.lfw_dir:
evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder,
embeddings, label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer)
sess.close()
return model_dir
def main(args):
dataset = facenet.get_dataset(args.dataset_dir)
with tf.Graph().as_default():
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(dataset)
nrof_images = len(image_list)
image_indices = range(nrof_images)
image_batch, label_batch = facenet.read_and_augment_data(image_list,
image_indices, args.image_size, args.batch_size, None,
False, False, False, nrof_preprocess_threads=4, shuffle=False)
model_exp = os.path.expanduser(args.model_file)
with gfile.FastGFile(model_exp,'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
input_map={'input':image_batch, 'phase_train':False}
tf.import_graph_def(graph_def, input_map=input_map, name='net')
embeddings = tf.get_default_graph().get_tensor_by_name("net/embeddings:0")
with tf.Session() as sess:
tf.train.start_queue_runners(sess=sess)
embedding_size = int(embeddings.get_shape()[1])
nrof_batches = int(math.ceil(nrof_images / args.batch_size))
nrof_classes = len(dataset)
label_array = np.array(label_list)
class_names = [cls.name for cls in dataset]
nrof_examples_per_class = [ len(cls.image_paths) for cls in dataset ]
class_variance = np.zeros((nrof_classes,))
class_center = np.zeros((nrof_classes,embedding_size))
distance_to_center = np.ones((len(label_list),))*np.NaN
emb_array = np.zeros((0,embedding_size))
idx_array = np.zeros((0,), dtype=np.int32)
lab_array = np.zeros((0,), dtype=np.int32)
index_arr = np.append(0, np.cumsum(nrof_examples_per_class))
for i in range(nrof_batches):
t = time.time()
emb, idx = sess.run([embeddings, label_batch])
emb_array = np.append(emb_array, emb, axis=0)
idx_array = np.append(idx_array, idx, axis=0)
lab_array = np.append(lab_array, label_array[idx], axis=0)
for cls in set(lab_array):
cls_idx = np.where(lab_array==cls)[0]
if cls_idx.shape[0]==nrof_examples_per_class[cls]:
# We have calculated all the embeddings for this class
i2 = np.argsort(idx_array[cls_idx])
emb_class = emb_array[cls_idx,:]
emb_sort = emb_class[i2,:]
center = np.mean(emb_sort, axis=0)
diffs = emb_sort - center
dists_sqr = np.sum(np.square(diffs), axis=1)
class_variance[cls] = np.mean(dists_sqr)
class_center[cls,:] = center
distance_to_center[index_arr[cls]:index_arr[cls+1]] = np.sqrt(dists_sqr)
emb_array = np.delete(emb_array, cls_idx, axis=0)
idx_array = np.delete(idx_array, cls_idx, axis=0)
lab_array = np.delete(lab_array, cls_idx, axis=0)
print('Batch %d in %.3f seconds' % (i, time.time()-t))
print('Writing filtering data to %s' % args.data_file_name)
mdict = {'class_names':class_names, 'image_list':image_list, 'label_list':label_list, 'distance_to_center':distance_to_center }
with h5py.File(args.data_file_name, 'w') as f:
for key, value in iteritems(mdict):
f.create_dataset(key, data=value)
def main(args):
network = importlib.import_module(args.model_def)
subdir = 'Finger'
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(
log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir,
'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32,
name='learning_rate')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_placeholder = tf.placeholder(tf.float32,
shape=(None, 150, 4),
name='image')
dynamic_alpha_placeholder = tf.placeholder(
tf.float32, shape=(), name='dynamic_alpha_placeholder')
prelogits, _ = network.inference(
image_placeholder,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Split embeddings into anchor, positive and negative and calculate triplet loss
anchor, positive, negative = tf.unstack(
tf.reshape(embeddings, [-1, 3, args.embedding_size]), 3, 1)
triplet_loss = facenet.triplet_loss(anchor, positive, negative,
dynamic_alpha_placeholder)
# learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step, args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
learning_rate = learning_rate_placeholder
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([triplet_loss] + regularization_losses,
name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
extra_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(extra_ops):
if args.optimizer == 'ADAGRAD':
opt = tf.train.AdagradOptimizer(learning_rate)
elif args.optimizer == 'ADADELTA':
opt = tf.train.AdadeltaOptimizer(learning_rate,
rho=0.9,
epsilon=1e-6)
elif args.optimizer == 'ADAM':
opt = tf.train.AdamOptimizer(learning_rate,
beta1=0.9,
beta2=0.999,
epsilon=0.1)
elif args.optimizer == 'RMSPROP':
opt = tf.train.RMSPropOptimizer(learning_rate,
decay=0.9,
momentum=0.9,
epsilon=1.0)
elif args.optimizer == 'MOM':
opt = tf.train.MomentumOptimizer(learning_rate,
0.9,
use_nesterov=True)
else:
raise ValueError('Invalid optimization algorithm')
train_op = opt.minimize(total_loss)
# train_op = facenet.train(total_loss, global_step, args.optimizer,
# learning_rate, args.moving_average_decay, tf.global_variables())
# Create a saver
saver = tf.train.Saver(tf.global_variables(), max_to_keep=10)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# Initialize variables
sess.run(tf.global_variables_initializer(),
feed_dict={phase_train_placeholder: True})
sess.run(tf.local_variables_initializer(),
feed_dict={phase_train_placeholder: True})
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
# saver.restore(sess,'./models/siamese/Finger/model-Finger.ckpt-548')
# saver.save(sess, 'c3d_lstm/')
epoch = 1
final_loss = 0.0
count = 0.0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
# epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, train_set, epoch, image_placeholder,
learning_rate_placeholder, phase_train_placeholder,
global_step, embeddings, total_loss, train_op,
summary_op, summary_writer, args.embedding_size, anchor,
positive, negative, triplet_loss,
dynamic_alpha_placeholder, final_loss, count)
epoch += 1
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer,
model_dir, subdir, epoch)
global epoch_list
global alpha_list
# plt.plot(epoch_list,alpha_list)
# plt.show()
# plt.savefig('alpha-vs-epoch.png')
file_for_alpha.write(epoch_list)
file_for_alpha.write(alpha_list)
return model_dir
def main(args):
network = importlib.import_module(args.model_def)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir):
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir):
os.makedirs(model_dir)
np.random.seed(seed=args.seed)
random.seed(args.seed)
train_set = facenet.get_dataset(args.data_dir)
if args.filter_filename:
train_set = filter_dataset(train_set, os.path.expanduser(args.filter_filename),
args.filter_percentile, args.filter_min_nrof_images_per_class)
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list)>0, 'The dataset should not be empty'
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
index_queue = tf.train.range_input_producer(range_size, num_epochs=None,
shuffle=True, seed=None, capacity=32)
index_dequeue_op = index_queue.dequeue_many(args.batch_size*args.epoch_size, 'index_dequeue')
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,1), name='image_paths')
labels_placeholder = tf.placeholder(tf.int64, shape=(None,1), name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=256000,
dtypes=[tf.string, tf.int64],
shapes=[(1,), (1,)],
shared_name=None, name=None)
enqueue_op = input_queue.enqueue_many([image_paths_placeholder, labels_placeholder], name='enqueue_op')
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unstack(filenames):
file_contents = tf.read_file(filename)
image = tf.cast(tf.image.decode_image(file_contents, channels=3),tf.float32)
# if args.random_crop:
# image = tf.random_crop(image, [args.image_size, args.image_size, 3])
# #image = tf.image.resize_image_with_crop_or_pad(image, args.image_size, args.image_size)
# else:
# image = tf.image.resize_image_with_crop_or_pad(image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#image = tf.image.random_brightness(image,max_delta=30)
#image = tf.image.random_contrast(image,lower=0.8,upper=1.2)
#image = tf.image.random_saturation(image,lower=0.8,upper=1.2)
image.set_shape((112, 96, 3))
images.append(tf.subtract(image,127.5) * 0.0078125)
images_and_labels.append([images, label])
image_batch, label_batch = tf.train.batch_join(
images_and_labels, batch_size=batch_size_placeholder,
shapes=[(112, 96, 3), ()], enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'input')
label_batch = tf.identity(label_batch, 'label_batch')
print('Total number of classes: %d' % nrof_classes)
print('Total number of examples: %d' % len(image_list))
print('Building training graph')
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
AM_logits = AM_logits_compute(embeddings, label_batch, args, nrof_classes)
#AM_logits = Arc_logits(embeddings, label_batch, args, nrof_classes)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch, logits=AM_logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
#print('test',tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES))
for weights in slim.get_variables_by_name('kernel'):
kernel_regularization = tf.contrib.layers.l2_regularizer(args.weight_decay)(weights)
print(weights)
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, kernel_regularization)
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
if args.weight_decay==0:
total_loss = tf.add_n([cross_entropy_mean], name='total_loss')
else:
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss')
tf.add_to_collection('losses', total_loss)
#define two saver in case under 'finetuning on different dataset' situation
saver_load = tf.train.Saver(tf.trainable_variables(), max_to_keep=1)
saver_save = tf.train.Saver(tf.trainable_variables(), max_to_keep =1)
#train_op = facenet.train(total_loss, global_step, args.optimizer,
# learning_rate, args.moving_average_decay, tf.trainable_variables(), args.log_histograms)
#train_op = tf.train.AdamOptimizer(learning_rate).minimize(total_loss,global_step = global_step,var_list=tf.trainable_variables())
train_op = tf.train.MomentumOptimizer(learning_rate,momentum=0.9).minimize(total_loss,global_step=global_step,var_list=tf.trainable_variables())
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver_load.restore(sess, pretrained_model)
print('Running training')
epoch = 0
best_accuracy = 0.0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
train(args, sess, epoch, image_list, label_list, index_dequeue_op, enqueue_op, image_paths_placeholder, labels_placeholder,
learning_rate_placeholder, phase_train_placeholder, batch_size_placeholder, global_step,
total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file)
print('validation running...')
if args.lfw_dir:
#best_accuracy = evaluate_double(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, embeddings,
# label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer,best_accuracy, saver_save,model_dir,subdir,image_batch,args)
best_accuracy = evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, embeddings,
label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer,best_accuracy,saver_save,model_dir,subdir)
return model_dir
def main(argv=None): # pylint: disable=unused-argument
if FLAGS.model_name:
subdir = FLAGS.model_name
preload_model = True
else:
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
preload_model = False
log_dir = os.path.join(os.path.expanduser(FLAGS.logs_base_dir), subdir)
model_dir = os.path.join(os.path.expanduser(FLAGS.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.mkdir(model_dir)
np.random.seed(seed=FLAGS.seed)
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, validation_set = facenet.split_dataset(dataset, FLAGS.train_set_fraction, FLAGS.split_mode)
print('Model directory: %s' % model_dir)
with tf.Graph().as_default():
tf.set_random_seed(FLAGS.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, FLAGS.image_size, FLAGS.image_size, 3),
name='input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, phase_train=phase_train_placeholder)
# Split example embeddings into anchor, positive and negative
anchor, positive, negative = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(anchor, positive, negative)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, _ = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=0)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
with sess.as_default():
if preload_model:
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Training and validation loop
for epoch in range(FLAGS.max_nrof_epochs):
# Train for one epoch
step = train(sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Validate epoch
validate(sess, validation_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Save the model checkpoint after each epoch
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
graphdef_dir = os.path.join(model_dir, 'graphdef')
graphdef_filename = 'graph_def.pb'
if (not os.path.exists(os.path.join(graphdef_dir, graphdef_filename))):
print('Saving graph definition')
tf.train.write_graph(sess.graph_def, graphdef_dir, graphdef_filename, False)
def main(args):
network = importlib.import_module(args.model_def, 'inference')
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
# Read data and apply label preserving distortions
image_batch, label_batch = facenet.read_and_augument_data(image_list, label_list, args.image_size,
args.batch_size, args.max_nrof_epochs, args.random_crop, args.random_flip, args.nrof_preprocess_threads)
print('Total number of classes: %d' % nrof_classes)
print('Total number of examples: %d' % len(image_list))
print('Building training graph')
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=True, weight_decay=args.weight_decay)
logits = slim.fully_connected(prelogits, len(train_set), activation_fn=None,
weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits', reuse=False)
# Add DeCov regularization loss
if args.decov_loss_factor>0.0:
logits_decov_loss = facenet.decov_loss(logits) * args.decov_loss_factor
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, logits_decov_loss)
# Add center loss
update_centers = tf.no_op('update_centers')
if args.center_loss_factor>0.0:
prelogits_center_loss, update_centers = facenet.center_loss(prelogits, label_batch, args.center_loss_alfa)
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.scalar_summary('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits, label_batch, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, tf.all_variables(), args.log_histograms)
# Evaluation
print('Building evaluation graph')
lfw_label_list = range(0,len(lfw_paths))
assert (len(lfw_paths) % args.lfw_batch_size == 0), "The number of images in the LFW test set need to be divisible by the lfw_batch_size"
eval_image_batch, eval_label_batch = facenet.read_and_augument_data(lfw_paths, lfw_label_list, args.image_size,
args.lfw_batch_size, None, False, False, args.nrof_preprocess_threads, shuffle=False)
# Node for input images
eval_image_batch.set_shape((None, args.image_size, args.image_size, 3))
eval_image_batch = tf.identity(eval_image_batch, name='input')
eval_prelogits, _ = network.inference(eval_image_batch, 1.0,
phase_train=False, weight_decay=0.0, reuse=True)
eval_embeddings = tf.nn.l2_normalize(eval_prelogits, 1, 1e-10, name='embeddings')
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.initialize_all_variables())
sess.run(tf.initialize_local_variables())
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
tf.train.start_queue_runners(sess=sess)
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
print('Running training')
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, epoch, learning_rate_placeholder, global_step,
total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file,
update_centers)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step)
# Evaluate on LFW
if args.lfw_dir:
evaluate(sess, eval_embeddings, eval_label_batch, actual_issame, args.lfw_batch_size, args.seed,
args.lfw_nrof_folds, log_dir, step, summary_writer)
return model_dir
def main(args):
with tf.Graph().as_default():
with tf.compat.v1.Session() as sess:
np.random.seed(seed=args.seed)
if args.use_split_dataset:
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(
dataset_tmp, args.min_nrof_images_per_class,
args.nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.compat.v1.get_default_graph(
).get_tensor_by_name("input:0")
embeddings = tf.compat.v1.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.compat.v1.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
pathName = []
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
for j in range(len(paths_batch)):
pathName.append(paths_batch[j])
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(
args.classifier_filename)
if (args.mode == 'TRAIN'):
# Train classifier
print('Training classifier')
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
elif (args.mode == 'CLASSIFY'):
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile,
encoding="latin1")
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
predictions = model.predict_proba(emb_array)
#print (predictions)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
scoreDic = {}
for i in range(len(predictions[1])):
#print(class_names[i],predictions[1][i])
scoreDic[class_names[i]] = predictions[1][i]
sorted_d = sorted(scoreDic.items(), key=lambda x: x[1])
#print(sorted_d)
# equivalent version
# sorted_d = sorted(d.items(), key=lambda (k,v): v)
print(emb_array)
#file1 = open('classify_result2.txt','w')
resultDic = {}
print(predictions.shape)
print(
sorted(range(len(predictions[1])),
key=lambda i: predictions[1][i],
reverse=True)[:5])
top5 = sorted(range(len(predictions[1])),
key=lambda i: predictions[1][i],
reverse=True)[:5]
for i in top5:
print(class_names[i])
print(predictions[1][i])
for i in range(len(best_class_indices)):
print('%s\t%s\t%.3f' %
(pathName[i], class_names[best_class_indices[i]],
best_class_probabilities[i]))
#print class_names
#print
#file1.write('%s\t%s\t%.3f' % (pathName[i], class_names[best_class_indices[i]], best_class_probabilities[i])+'\n')
resultDic[pathName[i]] = (
class_names[best_class_indices[i]],
best_class_probabilities[i], emb_array[i])
#file1.write(pathName[i]+'\t'+class_names[best_class_indices[i]]+'\t'+best_class_probabilities[i]+'\n')
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
pickle.dump(resultDic,
open("results/" + args.output + ".p", "wb"))
import shutil
import facenet
import os
dataset = facenet.get_dataset('dataset')
class_names = [cls.name.replace('_', ' ') for cls in dataset]
for i, name in enumerate(class_names):
if (name != 'Justin' and name != 'Arun' and name != 'Nijo'):
shutil.rmtree('dataset\\' + name)
os.system("python create_emb.py")
print("finish reset")
def main(args):
img_mean = np.array([134.10714722, 102.52040863, 87.15436554])
img_stddev = np.sqrt(
np.array([3941.30175781, 2856.94287109, 2519.35791016]))
vae_def = importlib.import_module(args.vae_def)
vae = vae_def.Vae(args.latent_var_size)
gen_image_size = vae.get_image_size()
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
log_file_name = os.path.join(model_dir, 'logs.h5')
# Write arguments to a text file
facenet.write_arguments_to_file(args,
os.path.join(model_dir, 'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, model_dir, ' '.join(sys.argv))
with tf.Graph().as_default():
tf.compat.v1.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
train_set = facenet.get_dataset(args.data_dir)
image_list, _ = facenet.get_image_paths_and_labels(train_set)
# Create the input queue
input_queue = tf.compat.v1.train.string_input_producer(image_list,
shuffle=True)
nrof_preprocess_threads = 4
image_per_thread = []
for _ in range(nrof_preprocess_threads):
file_contents = tf.io.read_file(input_queue.dequeue())
image = tf.image.decode_image(file_contents, channels=3)
image = tf.image.resize_with_crop_or_pad(image,
args.input_image_size,
args.input_image_size)
image.set_shape((args.input_image_size, args.input_image_size, 3))
image = tf.cast(image, tf.float32)
#pylint: disable=no-member
image_per_thread.append([image])
images = tf.compat.v1.train.batch_join(
image_per_thread,
batch_size=args.batch_size,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=False)
# Normalize
images_norm = (images - img_mean) / img_stddev
# Resize to appropriate size for the encoder
images_norm_resize = tf.image.resize(images_norm,
(gen_image_size, gen_image_size))
# Create encoder network
mean, log_variance = vae.encoder(images_norm_resize, True)
epsilon = tf.random.normal(
(tf.shape(input=mean)[0], args.latent_var_size))
std = tf.exp(log_variance / 2)
latent_var = mean + epsilon * std
# Create decoder network
reconstructed_norm = vae.decoder(latent_var, True)
# Un-normalize
reconstructed = (reconstructed_norm * img_stddev) + img_mean
# Create reconstruction loss
if args.reconstruction_loss_type == 'PLAIN':
images_resize = tf.image.resize(images,
(gen_image_size, gen_image_size))
reconstruction_loss = tf.reduce_mean(input_tensor=tf.reduce_sum(
input_tensor=tf.pow(images_resize - reconstructed, 2)))
elif args.reconstruction_loss_type == 'PERCEPTUAL':
network = importlib.import_module(args.model_def)
reconstructed_norm_resize = tf.image.resize(
reconstructed_norm,
(args.input_image_size, args.input_image_size))
# Stack images from both the input batch and the reconstructed batch in a new tensor
shp = [-1] + images_norm.get_shape().as_list()[1:]
input_images = tf.reshape(
tf.stack([images_norm, reconstructed_norm_resize], axis=0),
shp)
_, end_points = network.inference(input_images,
1.0,
phase_train=False,
bottleneck_layer_size=128,
weight_decay=0.0)
# Get a list of feature names to use for loss terms
feature_names = args.loss_features.replace(' ', '').split(',')
# Calculate L2 loss between original and reconstructed images in feature space
reconstruction_loss_list = []
for feature_name in feature_names:
feature_flat = slim.flatten(end_points[feature_name])
image_feature, reconstructed_feature = tf.unstack(tf.reshape(
feature_flat, [2, args.batch_size, -1]),
num=2,
axis=0)
reconstruction_loss = tf.reduce_mean(
input_tensor=tf.reduce_sum(input_tensor=tf.pow(
image_feature - reconstructed_feature, 2)),
name=feature_name + '_loss')
reconstruction_loss_list.append(reconstruction_loss)
# Sum up the losses in for the different features
reconstruction_loss = tf.add_n(reconstruction_loss_list,
'reconstruction_loss')
else:
pass
# Create KL divergence loss
kl_loss = kl_divergence_loss(mean, log_variance)
kl_loss_mean = tf.reduce_mean(input_tensor=kl_loss)
total_loss = args.alfa * kl_loss_mean + args.beta * reconstruction_loss
learning_rate = tf.compat.v1.train.exponential_decay(
args.initial_learning_rate,
global_step,
args.learning_rate_decay_steps,
args.learning_rate_decay_factor,
staircase=True)
# Calculate gradients and make sure not to include parameters for the perceptual loss model
opt = tf.compat.v1.train.AdamOptimizer(learning_rate)
grads = opt.compute_gradients(total_loss,
var_list=get_variables_to_train())
# Apply gradients
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
with tf.control_dependencies([apply_gradient_op]):
train_op = tf.no_op(name='train')
# Create a saver
saver = tf.compat.v1.train.Saver(tf.compat.v1.trainable_variables(),
max_to_keep=3)
facenet_saver = tf.compat.v1.train.Saver(
get_facenet_variables_to_restore())
# Start running operations on the Graph
gpu_memory_fraction = 1.0
gpu_options = tf.compat.v1.GPUOptions(
per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.compat.v1.Session(config=tf.compat.v1.ConfigProto(
gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.compat.v1.global_variables_initializer())
sess.run(tf.compat.v1.local_variables_initializer())
coord = tf.train.Coordinator()
tf.compat.v1.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if args.reconstruction_loss_type == 'PERCEPTUAL':
if not args.pretrained_model:
raise ValueError(
'A pretrained model must be specified when using perceptual loss'
)
pretrained_model_exp = os.path.expanduser(
args.pretrained_model)
print('Restoring pretrained model: %s' % pretrained_model_exp)
facenet_saver.restore(sess, pretrained_model_exp)
log = {
'total_loss': np.zeros((0, ), np.float),
'reconstruction_loss': np.zeros((0, ), np.float),
'kl_loss': np.zeros((0, ), np.float),
'learning_rate': np.zeros((0, ), np.float),
}
step = 0
print('Running training')
while step < args.max_nrof_steps:
start_time = time.time()
step += 1
save_state = step > 0 and (step % args.save_every_n_steps == 0
or step == args.max_nrof_steps)
if save_state:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_, rec_ = sess.run(
[
train_op, reconstruction_loss, kl_loss_mean,
total_loss, learning_rate, reconstructed
])
img = facenet.put_images_on_grid(rec_, shape=(16, 8))
misc.imsave(
os.path.join(model_dir,
'reconstructed_%06d.png' % step), img)
else:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_ = sess.run(
[
train_op, reconstruction_loss, kl_loss_mean,
total_loss, learning_rate
])
log['total_loss'] = np.append(log['total_loss'], total_loss_)
log['reconstruction_loss'] = np.append(
log['reconstruction_loss'], reconstruction_loss_)
log['kl_loss'] = np.append(log['kl_loss'], kl_loss_mean_)
log['learning_rate'] = np.append(log['learning_rate'],
learning_rate_)
duration = time.time() - start_time
print(
'Step: %d \tTime: %.3f \trec_loss: %.3f \tkl_loss: %.3f \ttotal_loss: %.3f'
% (step, duration, reconstruction_loss_, kl_loss_mean_,
total_loss_))
if save_state:
print('Saving checkpoint file')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess,
checkpoint_path,
global_step=step,
write_meta_graph=False)
print('Saving log')
with h5py.File(log_file_name, 'w') as f:
for key, value in iteritems(log):
f.create_dataset(key, data=value)
def main(args):
# tf_config = tf.ConfigProto()
# tf_config.gpu_options.per_process_gpu_memory_fraction = 1
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
if args.use_split_dataset:
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(
dataset_tmp, args.min_nrof_images_per_class,
args.nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
raw_paths, raw_labels = facenet.get_image_paths_and_labels(dataset)
random_list = range(0, len(raw_paths))
random.shuffle(random_list)
paths = []
labels = []
for index in random_list:
paths.append(raw_paths[index])
labels.append(raw_labels[index])
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
#emb_array = np.zeros((args.batch_size, embedding_size))
mlp_images_placeholder = tf.placeholder(
tf.float32, shape=(None, int(embedding_size)))
mlp_labels_placeholder = tf.placeholder(tf.int32, shape=(None))
global_step = tf.Variable(0, name='global_step', trainable=False)
regularizer = tf.contrib.layers.l2_regularizer(
args.regularization_rate)
#learning_rate = tf.train.exponential_decay(args.learning_rate_base, global_step, args.round_numbers, args.learning_rate_decay, staircase=True)
learning_rate = 0.01
tf.summary.scalar('learning_rate', learning_rate)
logits = mlp.inference(mlp_images_placeholder, int(embedding_size),
args.hidden1, args.hidden2,
args.number_class, regularizer)
entropy_loss = mlp.loss(logits, mlp_labels_placeholder)
tf.summary.scalar('entropy_loss', entropy_loss)
regularizer_loss = tf.add_n(tf.get_collection('regularizer_item'))
tf.summary.scalar('regularization_loss', regularizer_loss)
total_loss = entropy_loss + regularizer_loss
tf.summary.scalar('total_loss', total_loss)
train_op = mlp.training(total_loss, learning_rate, global_step)
summary = tf.summary.merge_all()
init = tf.global_variables_initializer()
saver = tf.train.Saver(tf.trainable_variables(),
max_to_keep=100000)
summary_writer = tf.summary.FileWriter(args.log_dir, sess.graph)
sess.run(init)
i = -1
for step in xrange(1000000):
i = i + 1
if i >= nrof_batches_per_epoch:
i = 0
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array = np.zeros((end_index - start_index, embedding_size))
emb_array[0:end_index - start_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
label_array = labels[start_index:end_index]
start_time = time.time()
_, loss_value = sess.run(
[train_op, total_loss], {
mlp_images_placeholder: emb_array,
mlp_labels_placeholder: label_array
})
duration = time.time() - start_time
# write the summaries and print an overview fairly often.
print('step {}: loss = {} ({} sec)'.format(
step, loss_value, duration))
if step % 100 == 0:
# update the events file.
summary_str = sess.run(
summary, {
mlp_images_placeholder: emb_array,
mlp_labels_placeholder: label_array
})
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
# save a checkpoint and evaluate the model periodically.
#if (step + 1) % 1000 == 0 or (step + 1) == args.max_steps:
if step >= 10000 and step % 1000 == 0:
checkpoint_path = os.path.join(args.log_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def retrain_model(self, incremental):
global labels
global emb_array
global class_names
if incremental is True:
dataset, append_index = facenet.append_dataset(
data_dir, class_names)
paths, self.append_labels = facenet.get_image_paths_and_labels(
dataset, append_index)
self.append_class_names = [
cls.name.replace('_', ' ') for cls in dataset
]
else:
dataset, append_index = facenet.get_dataset(data_dir)
paths, labels = facenet.get_image_paths_and_labels(
dataset, append_index)
class_names = [cls.name.replace('_', ' ') for cls in dataset]
np.random.seed(seed=666)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
# Create a list of class names
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
if incremental is True:
print("new people added: ")
print(self.append_class_names)
# Get input and output tensors
images_placeholder = self.graph.get_tensor_by_name("input:0")
embeddings = self.graph.get_tensor_by_name("embeddings:0")
phase_train_placeholder = self.graph.get_tensor_by_name(
"phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(math.ceil(1.0 * nrof_images / 90))
self.append_emb_array = np.zeros((nrof_images, embedding_size))
for i in tqdm(range(nrof_batches_per_epoch)):
start_index = i * 90
end_index = min((i + 1) * 90, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False, 160)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
self.append_emb_array[start_index:end_index, :] = self.sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(classifier_model)
print('Training classifier')
if incremental is True:
self.incremental_training(self.append_emb_array,
self.append_labels,
self.append_class_names)
print(len(emb_array))
print(class_names)
#X_train, X_test, y_train, y_test = train_test_split(emb_array, labels, test_size=0.25)
#self.model = SGDClassifier(loss='log', verbose=True, n_jobs=-1, n_iter=1000, alpha=1e-5,
# tol=None, shuffle=True, random_state=100, penalty='l2')
#self.model = SVC(kernel='rbf', probability=True, verbose=True, cache_size=1024)
#self.model = KNeighborsClassifier(n_neighbors=1, algorithm='auto')
print('Start building model')
start = time.time()
#param_grid = {'C': [1e3, 5e3, 1e4, 5e4, 1e5],
# 'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
#self.model = GridSearchCV(SVC(kernel='rbf', cache_size=2048, probability=True), param_grid, n_jobs=-1)
model.fit(emb_array, labels)
#self.model.fit(X_train, y_train)
end = time.time()
print("Fit Time: {0:4f}s".format(end - start))
print('Build model done')
if incremental is False:
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((emb_array, labels, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
return 'Success'
def main(args):
network = importlib.import_module(args.model_def, 'inference')
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
if args.pretrained_model:
print('Pre-trained model: %s' % os.path.expanduser(args.pretrained_model))
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(None, args.image_size, args.image_size, 3), name='input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
# Build the inference graph
prelogits, _ = network.inference(images_placeholder, args.keep_probability,
phase_train=True, weight_decay=args.weight_decay)
pre_embeddings = slim.fully_connected(prelogits, 128, activation_fn=None, scope='Embeddings', reuse=False)
# Split example embeddings into anchor, positive and negative and calculate triplet loss
embeddings = tf.nn.l2_normalize(pre_embeddings, 1, 1e-10, name='embeddings')
anchor, positive, negative = tf.split(0, 3, embeddings)
triplet_loss = facenet.triplet_loss(anchor, positive, negative, args.alpha)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.scalar_summary('learning_rate', learning_rate)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([triplet_loss] + regularization_losses, name='total_loss')
# Create list with variables to restore
restore_vars = []
update_gradient_vars = []
if args.pretrained_model:
for var in tf.all_variables():
if not 'Embeddings/' in var.op.name:
restore_vars.append(var)
else:
update_gradient_vars.append(var)
else:
restore_vars = tf.all_variables()
update_gradient_vars = tf.all_variables()
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, update_gradient_vars)
# Create a saver
restore_saver = tf.train.Saver(restore_vars)
saver = tf.train.Saver(tf.all_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# Initialize variables
sess.run(tf.initialize_all_variables())
sess.run(tf.initialize_local_variables())
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
tf.train.start_queue_runners(sess=sess)
with sess.as_default():
if args.pretrained_model:
restore_saver.restore(sess, os.path.expanduser(args.pretrained_model))
# Training and validation loop
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
step = train(args, sess, train_set, epoch, images_placeholder,
learning_rate_placeholder, global_step, embeddings, total_loss, train_op, summary_op, summary_writer)
if args.lfw_dir:
_, _, accuracy, val, val_std, far = lfw.validate(sess, lfw_paths,
actual_issame, args.seed, 60, images_placeholder, phase_train_placeholder, embeddings, nrof_folds=args.lfw_nrof_folds)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
# Add validation loss and accuracy to summary
summary = tf.Summary()
#pylint: disable=maybe-no-member
summary.value.add(tag='lfw/accuracy', simple_value=np.mean(accuracy))
summary.value.add(tag='lfw/val_rate', simple_value=val)
summary_writer.add_summary(summary, step)
# Save the model checkpoint
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
return model_dir
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
if args.use_split_dataset:
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(dataset_tmp, args.min_nrof_images_per_class, args.nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert(len(cls.image_paths) > 0, 'There must be at least one image for each class in the dataset')
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False, args.image_size)
feed_dict = {images_placeholder: images, phase_train_placeholder: False}
emb_array[start_index:end_index, :] = sess.run(embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(args.classifier_filename)
if (args.mode == 'TRAIN'):
# Train classifier
print('Training classifier')
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' % classifier_filename_exp)
elif (args.mode == 'CLASSIFY'):
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' % classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s: %.3f' % (i, class_names[best_class_indices[i]], best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
def train():
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, test_set = facenet.split_dataset(dataset, 0.9)
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, 96, 96, 3), name='Input')
# Build a Graph that computes the logits predictions from the inference model
embeddings = facenet.inference_no_batch_norm_deeper(images_placeholder, tf.constant(True))
#embeddings = facenet.inference(images_placeholder, tf.constant(False))
# Split example embeddings into anchor, positive and negative
#a, p, n = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss_modified(embeddings)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, grads = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
check_num = tf.add_check_numerics_ops()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def)
epoch = 1
with sess.as_default():
while epoch<FLAGS.max_nrof_epochs:
batch_number = 0
while batch_number<FLAGS.epoch_size:
print('Loading new data')
image_data, num_per_class = facenet.load_data(train_set)
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = FLAGS.people_per_batch*FLAGS.images_per_person
nrof_batches_per_epoch = int(np.floor(nrof_examples_per_epoch/FLAGS.batch_size))
#for i in xrange(nrof_batches_per_epoch):
#feed_dict = facenet.get_batch(images_placeholder, image_data, i)
#emb_list += sess.run([embeddings], feed_dict=feed_dict)
#emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
## Select triplets based on the embeddings
#apn, nrof_random_negs, nrof_triplets = facenet.select_triplets(emb_array, num_per_class, image_data)
#duration = time.time() - start_time
#print('(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' % (nrof_random_negs, nrof_triplets, duration))
count = 0
# while count<nrof_triplets*3 and batch_number<FLAGS.epoch_size:
while batch_number<FLAGS.epoch_size:
start_time = time.time()
# feed_dict = facenet.get_batch(images_placeholder, apn, batch_number)
feed_dict = facenet.get_batch(images_placeholder, image_data, batch_number)
grad_tensors, grad_vars = zip(*grads)
grads_eval = sess.run(grad_tensors, feed_dict=feed_dict)
for gt, gv in zip(grads_eval, grad_vars):
print('%40s: %6d %6f %6f' % (gv.op.name, np.sum(np.isnan(gt)), np.max(gt), np.min(gt)))
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f' % (epoch, batch_number, FLAGS.epoch_size, duration, err))
batch_number+=1
count+=FLAGS.batch_size
epoch+=1
# Save the model checkpoint periodically.
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=epoch*FLAGS.epoch_size+batch_number)
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
if args.use_split_dataset:
print("Printing the data_dir args!")
print(args.data_dir)
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(
dataset_tmp, args.min_nrof_images_per_class,
args.nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
### The paths and labels here has been flattened and they are pair and pair accordingly ###
### The labels here are just ids ###
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the image to vector embedding model
print('Loading feature extraction model')
print(args.model)
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
### The embedding size here is 512 because the author claims that increasing it to 512 ###
### From 128 seems to give a better performance ! ###
embedding_size = embeddings.get_shape()[1]
print(embedding_size)
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
print(nrof_images)
print(nrof_batches_per_epoch)
emb_array = np.zeros((nrof_images, embedding_size))
print(emb_array.shape)
### embedding array here has a shape of (1202, 512) basically has 1202 rows and 512 columns for embeddings ###
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
print(emb_array)
classifier_filename_exp = os.path.expanduser(
args.classifier_filename)
print(classifier_filename_exp)
if (args.mode == 'TRAIN'):
# Train classifier
print('Training classifier')
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
elif (args.mode == 'CLASSIFY'):
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
### emb_array is already in the format that the prediction will take ###
predictions = model.predict_proba(emb_array)
print("Output shape of prediction here is: ",
predictions.shape)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s: %.3f' %
(i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
# Simply find the average accuracy by finding the mean of the entire accuracy whenever
# There is a class that matches
print(labels)
print(best_class_indices)
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
def main(args):
# count = 1
gpuid = 0
detector = RetinaFace(
'/home/tmt/Documents/insightface/RetinaFace/model/retinaface-R50/', 0,
gpuid, 'net3')
sleep(random.random())
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
dataset = facenet.get_dataset(args.input_dir)
print('Creating networks and loading parameters')
# with tf.Graph().as_default():
# gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
# sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
# with sess.as_default():
# pnet, rnet, onet = align.detect_face.create_mtcnn(sess, None)
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
# Add a random key to the filename to allow alignment using multiple processes
random_key = np.random.randint(0, high=99999)
bounding_boxes_filename = os.path.join(
output_dir, 'bounding_boxes_%05d.txt' % random_key)
with open(bounding_boxes_filename, "w") as text_file:
nrof_images_total = 0
nrof_successfully_aligned = 0
if args.random_order:
random.shuffle(dataset)
for cls in tqdm(dataset):
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
if args.random_order:
random.shuffle(cls.image_paths)
for image_path in cls.image_paths:
thresh = 0.8
scales = [1024, 1980]
nrof_images_total += 1
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir,
filename + '.png')
print(image_path)
if not os.path.exists(output_filename):
try:
# img = misc.imread(image_path)
img = cv2.imread(image_path)
print('image shape', img.shape)
im_shape = img.shape
target_size = scales[0]
max_size = scales[1]
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
#im_scale = 1.0
# if im_size_min>target_size or im_size_max>max_size:
im_scale = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(im_scale * im_size_max) > max_size:
im_scale = float(max_size) / float(im_size_max)
print('im_scale', im_scale)
scales = [im_scale]
flip = False
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim < 2:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
continue
if img.ndim == 2:
img = facenet.to_rgb(img)
img = img[:, :, 0:3]
bounding_boxes, landmarks = detector.detect(
img, thresh, scales=scales, do_flip=flip)
# bounding_boxes, _ = align.detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor)
print('-------------bounding----------------',
bounding_boxes)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
det_arr = []
img_size = np.asarray(img.shape)[0:2]
if nrof_faces > 1:
if args.detect_multiple_faces:
for i in range(nrof_faces):
det_arr.append(np.squeeze(det[i]))
else:
bounding_box_size = (
det[:, 2] - det[:, 0]) * (det[:, 3] -
det[:, 1])
img_center = img_size / 2
offsets = np.vstack([
(det[:, 0] + det[:, 2]) / 2 -
img_center[1],
(det[:, 1] + det[:, 3]) / 2 -
img_center[0]
])
offset_dist_squared = np.sum(
np.power(offsets, 2.0), 0)
# some extra weight on the centering
index = np.argmax(bounding_box_size -
offset_dist_squared *
2.0)
det_arr.append(det[index, :])
else:
det_arr.append(np.squeeze(det))
for i, det in enumerate(det_arr):
det = np.squeeze(det)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - args.margin / 2, 0)
bb[1] = np.maximum(det[1] - args.margin / 2, 0)
bb[2] = np.minimum(det[2] + args.margin / 2,
img_size[1])
bb[3] = np.minimum(det[3] + args.margin / 2,
img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = misc.imresize(
cropped,
(args.image_size, args.image_size),
interp='bilinear')
nrof_successfully_aligned += 1
filename_base, file_extension = os.path.splitext(
output_filename)
if args.detect_multiple_faces:
output_filename_n = "{}_{}{}".format(
filename_base, i, file_extension)
else:
output_filename_n = "{}{}".format(
filename_base, file_extension)
misc.imsave(output_filename_n, scaled)
text_file.write('%s %d %d %d %d\n' %
(output_filename_n, bb[0],
bb[1], bb[2], bb[3]))
else:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' %
nrof_successfully_aligned)
def main(args):
network = importlib.import_module(args.model_def, 'inference')
if args.model_name:
subdir = args.model_name
preload_model = True
else:
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
preload_model = False
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.mkdir(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.mkdir(model_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
print('Model directory: %s' % model_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(None, args.image_size, args.image_size, 3), name='input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
embeddings = network.inference(images_placeholder, args.pool_type, args.use_lrn,
args.keep_probability, phase_train=phase_train_placeholder, weight_decay=args.weight_decay)
# Split example embeddings into anchor, positive and negative
anchor, positive, negative = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(anchor, positive, negative, args.alpha)
# Calculate the total loss
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([loss] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, _ = facenet.train(total_loss, global_step, args.optimizer, args.learning_rate,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, args.moving_average_decay)
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=0)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session()
sess.run(init)
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
with sess.as_default():
if preload_model:
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Training and validation loop
for epoch in range(args.max_nrof_epochs):
# Train for one epoch
step = train(args, sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
_, _, accuracy, val, val_std, far = lfw.validate(sess,
paths, actual_issame, args.seed, args.batch_size,
images_placeholder, phase_train_placeholder, embeddings, nrof_folds=args.lfw_nrof_folds)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
# Add validation loss and accuracy to summary
summary = tf.Summary()
summary.value.add(tag='lfw/accuracy', simple_value=np.mean(accuracy))
summary.value.add(tag='lfw/val_rate', simple_value=val)
summary_writer.add_summary(summary, step)
if (epoch % args.checkpoint_period == 0) or (epoch==args.max_nrof_epochs-1):
# Save the model checkpoint
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
return model_dir
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
if args.use_split_dataset:
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(
dataset_tmp, args.min_nrof_images_per_class,
args.nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(
args.classifier_filename)
#embfilename='20180402-114759'
#if not os.path.exists('D:\\facenet\\descriptors\\'+embfilename):
# os.mkdir('D:\\facenet\\descriptors\\'+embfilename)
#np.savetxt('D:\\facenet\\descriptors\\'+embfilename+'\\log1.gz', emb_array, fmt='%.32f', delimiter=',', newline='\n')
#print('Saved feature embeddings to file "%s"' % embfilename)
if (args.mode == 'TRAIN'):
# Train classifier
print('Training classifier')
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
elif (args.mode == 'CLASSIFY'):
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s: %.3f' %
(i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
labels = label_binarize(np.array(labels), classes=range(1, 21))
best_class_indices = label_binarize(
np.array(best_class_indices), classes=range(1, 21))
precision, recall, _ = precision_recall_curve(
labels.ravel(), best_class_indices.ravel())
average_precision = average_precision_score(labels,
best_class_indices,
average="micro")
print(
'Average precision score, micro-averaged over all classes: {0:0.2f}'
.format(average_precision))
plt.figure()
plt.step(recall, precision, color='b', alpha=0.2, where='post')
plt.fill_between(recall,
precision,
step='post',
alpha=0.2,
color='b')
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.ylim([0.0, 1.05])
plt.xlim([0.0, 1.0])
plt.title(
'Average precision score, micro-averaged over all classes: AP={0:0.2f}'
.format(average_precision))
def main(args):
np.random.seed(seed=args.seed)
random.seed(args.seed)
train_set = facenet.get_dataset(args.data_dir)
result_filename = os.path.join(os.path.expanduser(args.data_dir), 'statistics.txt')
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
# Get a list of image paths and their labels
image_list, _ = facenet.get_image_paths_and_labels(train_set)
nrof_images = len(image_list)
assert nrof_images>0, 'The dataset should not be empty'
input_queue = tf.train.string_input_producer(image_list, num_epochs=None,
shuffle=False, seed=None, capacity=32)
nrof_preprocess_threads = 4
images = []
for _ in range(nrof_preprocess_threads):
filename = input_queue.dequeue()
file_contents = tf.read_file(filename)
image = tf.image.decode_image(file_contents)
image = tf.image.resize_image_with_crop_or_pad(image, 160, 160)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
image = tf.cast(image, tf.float32)
images.append((image,))
image_batch = tf.train.batch_join(images, batch_size=100, allow_smaller_final_batch=True)
#mean = tf.reduce_mean(image_batch, reduction_indices=[0,1,2])
m, v = tf.nn.moments(image_batch, [1,2])
mean = tf.reduce_mean(m, 0)
variance = tf.reduce_mean(v, 0)
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)
with sess.as_default():
# Training and validation loop
print('Running training')
nrof_batches = nrof_images // args.batch_size
#nrof_batches = 20
means = np.zeros(shape=(nrof_batches, 3), dtype=np.float32)
variances = np.zeros(shape=(nrof_batches, 3), dtype=np.float32)
for i in range(nrof_batches):
means[i,:], variances[i,:] = sess.run([mean, variance])
if (i+1)%10==0:
print('Batch: %5d/%5d, Mean: %s, Variance: %s' % (i+1, nrof_batches, np.array_str(np.mean(means[:i,:],axis=0)), np.array_str(np.mean(variances[:i,:],axis=0))))
dataset_mean = np.mean(means,axis=0)
dataset_variance = np.mean(variances,axis=0)
print('Final mean: %s' % np.array_str(dataset_mean))
print('Final variance: %s' % np.array_str(dataset_variance))
with open(result_filename, 'w') as text_file:
print('Writing result to %s' % result_filename)
text_file.write('Mean: %.5f, %.5f, %.5f\n' % (dataset_mean[0], dataset_mean[1], dataset_mean[2]))
text_file.write('Variance: %.5f, %.5f, %.5f\n' % (dataset_variance[0], dataset_variance[1], dataset_variance[2]))
def collect_data(self):
output_dir = os.path.expanduser(self.output_datadir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
dataset = facenet.get_dataset(self.input_datadir)
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)
sess = tf.Session(config=tf.ConfigProto(
gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, './npy')
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 44
image_size = 182
# Add a random key to the filename to allow alignment using multiple processes
random_key = np.random.randint(0, high=99999)
bounding_boxes_filename = os.path.join(
output_dir, 'bounding_boxes_%05d.txt' % random_key)
with open(bounding_boxes_filename, "w") as text_file:
nrof_images_total = 0
nrof_successfully_aligned = 0
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
for image_path in cls.image_paths:
nrof_images_total += 1
filename = os.path.splitext(
os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir,
filename + '.png')
print("Image: %s" % image_path)
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim < 2:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
continue
if img.ndim == 2:
img = facenet.to_rgb(img)
print('to_rgb data dimension: ', img.ndim)
img = img[:, :, 0:3]
bounding_boxes, _ = detect_face.detect_face(
img, minsize, pnet, rnet, onet, threshold,
factor)
nrof_faces = bounding_boxes.shape[0]
print('No of Detected Face: %d' % nrof_faces)
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
img_size = np.asarray(img.shape)[0:2]
if nrof_faces > 1:
bounding_box_size = (
det[:, 2] - det[:, 0]) * (det[:, 3] -
det[:, 1])
img_center = img_size / 2
offsets = np.vstack([
(det[:, 0] + det[:, 2]) / 2 -
img_center[1],
(det[:, 1] + det[:, 3]) / 2 -
img_center[0]
])
offset_dist_squared = np.sum(
np.power(offsets, 2.0), 0)
index = np.argmax(
bounding_box_size -
offset_dist_squared * 2.0
) # some extra weight on the centering
det = det[index, :]
det = np.squeeze(det)
bb_temp = np.zeros(4, dtype=np.int32)
bb_temp[0] = det[0]
bb_temp[1] = det[1]
bb_temp[2] = det[2]
bb_temp[3] = det[3]
cropped_temp = img[bb_temp[1]:bb_temp[3],
bb_temp[0]:bb_temp[2], :]
scaled_temp = misc.imresize(
cropped_temp, (image_size, image_size),
interp='bilinear')
nrof_successfully_aligned += 1
misc.imsave(output_filename, scaled_temp)
text_file.write(
'%s %d %d %d %d\n' %
(output_filename, bb_temp[0], bb_temp[1],
bb_temp[2], bb_temp[3]))
else:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
return (nrof_images_total, nrof_successfully_aligned)
def main(args):
sleep(random.random())
# get the complete path of output directory
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# get the path of this program file
src_path, _ = os.path.split(os.path.realpath(__file__))
# Store some git revision info in a text file in the log directory
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
# get_dataset is a function which return a list of special objects
# this kind of object has two element, one is the class name,
# and the other is the path of all entry belonging to this class
dataset = facenet.get_dataset(args.input_dir)
# dataset = facenet.get_dataset_from_difference_sources(args.input_dir)
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = align.detect_face.create_mtcnn(sess, None)
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
# Add a random key to the filename to allow alignment using multiple processes
random_key = np.random.randint(0, high=99999)
bounding_boxes_filename = os.path.join(
output_dir, 'bounding_boxes_%05d.txt' % random_key)
with open(bounding_boxes_filename, "w") as text_file:
nrof_images_total = 0
nrof_successfully_aligned = 0
if args.random_order:
random.shuffle(dataset) # classes shuffle
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
if args.random_order:
random.shuffle(cls.image_paths) # images shuffle
for image_path in cls.image_paths:
nrof_images_total += 1
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir,
filename + '.png')
print(image_path)
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
# img = cv2.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
# make sure that all images are normal
# ----------------------------------------------
if img.ndim < 2: # an normal image should has at least two dimension(width and high)
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
continue
if img.ndim == 2: # an image which has only one channel
img = facenet.to_rgb(img)
img = img[:, :, 0:3]
# ----------------------------------------------
# bounding_boxes: faces of all person in this image
# _: five landmarks of each person in this image
bounding_boxes, _ = align.detect_face.detect_face(
img, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
# at least one face
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
img_size = np.asarray(img.shape)[0:2]
# more than one faces in this image
# -------------------------------------------------------------------
# if nrof_faces > 1:
# bounding_box_size = (det[:, 2]-det[:, 0])*(det[:, 3]-det[:, 1]) # width * high
# img_center = img_size / 2
#
# # how far is each person(center of face) from the center of this image
# offsets = np.vstack([(det[:, 0]+det[:, 2])/2-img_center[1], (det[:, 1]+det[:, 3])/2-img_center[0]])
# offset_dist_squared = np.sum(np.power(offsets, 2.0), 0)
#
# # choose the most import person in this image
# index = np.argmax(bounding_box_size-offset_dist_squared*2.0) # some extra weight on the centering
# det = det[index, :]
# -------------------------------------------------------------------
for det_no in range(nrof_faces):
each_det = np.squeeze(det[det_no])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(
each_det[0] - args.margin / 2, 0)
bb[1] = np.maximum(
each_det[1] - args.margin / 2, 0)
bb[2] = np.minimum(
each_det[2] + args.margin / 2, img_size[1])
bb[3] = np.minimum(
each_det[3] + args.margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = misc.imresize(
cropped,
(args.image_size, args.image_size),
interp='bilinear')
if nrof_faces > 1:
output_filename = os.path.join(
output_class_dir,
filename + '_%d.png' % (det_no))
misc.imsave(output_filename, scaled)
text_file.write('%s %d %d %d %d\n' %
(output_filename, bb[0], bb[1],
bb[2], bb[3]))
nrof_successfully_aligned += 1
else:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' %
nrof_successfully_aligned)
def main(args):
use_mlboard = False
mlboard = None
if client:
mlboard = client.Client()
try:
mlboard.apps.get()
except Exception:
mlboard = None
print('Do not use mlboard.')
else:
print('Use mlboard parameters logging.')
use_mlboard = True
if args.use_split_dataset:
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(dataset_tmp,
args.min_nrof_images_per_class,
args.nrof_train_images_per_class)
if args.mode == 'TRAIN':
dataset = train_set
elif args.mode == 'CLASSIFY':
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
update_data({'mode': args.mode}, use_mlboard, mlboard)
# Check that there are at least one training image per class
for cls in dataset:
assert len(
cls.image_paths
) > 0, 'There must be at least one image for each class in the dataset'
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
data = {
'num_classes': len(dataset),
'num_images': len(paths),
'model_path': args.model,
'image_size': args.image_size,
'data_dir': args.data_dir,
'batch_size': args.batch_size,
}
update_data(data, use_mlboard, mlboard)
# Load the model
print('Loading feature extraction model')
# Load driver
drv = driver.load_driver(args.driver)
# Instantinate driver
serving = drv()
serving.load_model(
args.model,
inputs='input:0,phase_train:0',
outputs='embeddings:0',
device=args.device,
)
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(math.ceil(1.0 * nrof_images /
args.batch_size))
emb_array = np.zeros((nrof_images, 512))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
for j in range(end_index - start_index):
print('Batch {} <-> {}'.format(paths_batch[j],
labels[start_index + j]))
images = facenet.load_data(paths_batch, False, False, args.image_size)
if serving.driver_name == 'tensorflow':
feed_dict = {'input:0': images, 'phase_train:0': False}
elif serving.driver_name == 'openvino':
input_name = list(serving.inputs.keys())[0]
# Transpose image for channel first format
images = images.transpose([0, 3, 1, 2])
feed_dict = {input_name: images}
else:
raise RuntimeError('Driver %s currently not supported' %
serving.driver_name)
outputs = serving.predict(feed_dict)
emb_array[start_index:end_index, :] = list(outputs.values())[0]
classifier_filename_exp = os.path.expanduser(args.classifier_filename)
if args.mode == 'TRAIN':
# Train classifier
print('Training classifier')
model = svm.SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
print('Classes:')
print(class_names)
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile, protocol=2)
print('Saved classifier model to file "%s"' % classifier_filename_exp)
elif args.mode == 'CLASSIFY':
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s: %.3f' % (i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
update_data({'accuracy': accuracy}, use_mlboard, mlboard)
print('Accuracy: %.3f' % accuracy)
if args.upload_model and accuracy >= args.upload_threshold:
timestamp = datetime.datetime.now().strftime('%s')
model_name = 'facenet-classifier'
version = '1.0.0-%s-%s' % (args.driver, timestamp)
print('Uploading model as %s:%s' % (model_name, version))
upload_model(use_mlboard, mlboard, classifier_filename_exp,
model_name, version)
def main(args):
sleep(random.random())
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
dataset = facenet.get_dataset(args.input_dir, args.has_classes)
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = align.detect_face.create_mtcnn(sess, None)
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
# Add a random key to the filename to allow alignment using multiple processes
random_key = np.random.randint(0, high=99999)
bounding_boxes_filename = os.path.join(
output_dir, 'bounding_boxes_%05d.txt' % random_key)
with open(bounding_boxes_filename, "w") as text_file:
nrof_images_total = 0
nrof_successfully_aligned = 0
if args.random_order:
random.shuffle(dataset)
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
if args.random_order:
random.shuffle(cls.image_paths)
for image_path in cls.image_paths:
nrof_images_total += 1
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir,
filename + '.png')
print(image_path)
if not os.path.exists(output_filename):
try:
img = Image.open(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
#if img.ndim<2:
# print('Unable to align "%s"' % image_path)
# text_file.write('%s\n' % (output_filename))
# continue
#if img.ndim == 2:
# img = facenet.to_rgb(img)
img = np.array(img)
bounding_boxes, _ = align.detect_face.detect_face(
img, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
img_size = np.asarray(img.shape)[0:2]
if nrof_faces > 1:
bounding_box_size = (det[:, 2] - det[:, 0]) * (
det[:, 3] - det[:, 1])
img_center = img_size / 2
offsets = np.vstack([
(det[:, 0] + det[:, 2]) / 2 -
img_center[1],
(det[:, 1] + det[:, 3]) / 2 - img_center[0]
])
offset_dist_squared = np.sum(
np.power(offsets, 2.0), 0)
index = np.argmax(
bounding_box_size - offset_dist_squared *
2.0) # some extra weight on the centering
det = det[index, :]
det = np.squeeze(det)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - args.margin / 2, 0)
bb[1] = np.maximum(det[1] - args.margin / 2, 0)
bb[2] = np.minimum(det[2] + args.margin / 2,
img_size[1])
bb[3] = np.minimum(det[3] + args.margin / 2,
img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = Image.fromarray(cropped.astype(
np.uint8), 'RGB').resize(
(args.image_size, args.image_size),
Image.BICUBIC)
nrof_successfully_aligned += 1
scaled.save(output_filename)
text_file.write(
'%s %d %d %d %d\n' %
(output_filename, bb[0], bb[1], bb[2], bb[3]))
else:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' %
nrof_successfully_aligned)
def main(args):
network = importlib.import_module(args.model_def)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(
log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir,
'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
#facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
random.seed(args.seed)
train_set = facenet.get_dataset(args.data_dir)
if args.filter_filename:
train_set = filter_dataset(train_set,
os.path.expanduser(args.filter_filename),
args.filter_percentile,
args.filter_min_nrof_images_per_class)
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(
os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default(), tf.device('/cpu:0'):
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list) > 0, 'The dataset should not be empty'
# Create a queue that produces indices into the image_list and label_list
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
index_queue = tf.train.range_input_producer(range_size,
num_epochs=None,
shuffle=True,
seed=None,
capacity=320)
index_dequeue_op = index_queue.dequeue_many(
args.batch_size * args.epoch_size, 'index_dequeue')
learning_rate_placeholder = tf.placeholder(tf.float32,
name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string,
shape=(None, 1),
name='image_paths')
labels_placeholder = tf.placeholder(tf.int64,
shape=(None, 1),
name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=1000000,
dtypes=[tf.string, tf.int64],
shapes=[(1, ), (1, )],
shared_name=None,
name=None)
enqueue_op = input_queue.enqueue_many(
[image_paths_placeholder, labels_placeholder], name='enqueue_op')
nrof_preprocess_threads = 12
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unstack(filenames):
file_contents = tf.read_file(filename)
image = tf.image.decode_image(file_contents, channels=3)
if args.random_rotate:
image = tf.py_func(facenet.random_rotate_image, [image],
tf.uint8)
if args.random_crop:
image = tf.random_crop(
image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(
image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
image_batch, label_batch = tf.train.batch_join(
images_and_labels,
batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()],
enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
label_batch = tf.identity(label_batch, 'label_batch')
print('Total number of classes: %d' % nrof_classes)
print('Total number of examples: %d' % len(image_list))
print('Building training graph')
def _add_loss_summaries(total_loss):
loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
losses = tf.get_collection('losses')
loss_averages_op = loss_averages.apply(losses + [total_loss])
# Attach a scalar summmary to all individual losses and the total loss; do the
# same for the averaged version of the losses.
for l in losses + [total_loss]:
# Name each loss as '(raw)' and name the moving average version of the loss
# as the original loss name.
tf.summary.scalar(l.op.name + ' (raw)', l)
tf.summary.scalar(l.op.name, loss_averages.average(l))
return loss_averages_op
def tower_loss(scope, image_batch, label_batch, keep_probability,
phase_train, bottleneck_layer_size, weight_decay,
nrof_classes, center_loss_factor, center_loss_alfa):
prelogits, _ = network.inference(image_batch, keep_probability,
phase_train,
bottleneck_layer_size,
weight_decay)
logits = slim.fully_connected(
prelogits,
nrof_classes,
activation_fn=None,
weights_initializer=tf.truncated_normal_initializer(
stddev=0.1),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits',
reuse=False)
embeddings = tf.nn.l2_normalize(prelogits,
1,
1e-10,
name='embeddings')
if center_loss_factor > 0.0:
prelogits_center_loss, _ = facenet.center_loss(
prelogits, label_batch, center_loss_alfa, nrof_classes)
tf.add_to_collection(
tf.GraphKeys.REGULARIZATION_LOSSES,
prelogits_center_loss * args.center_loss_factor)
# Calculate the average cross entropy loss across the batch
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch,
logits=logits,
name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy,
name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# Calculate the total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES, scope)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses,
name='total_loss')
return total_loss, regularization_losses, embeddings
def average_gradients(tower_grads):
average_grads = []
for grad_and_vars in zip(*tower_grads):
grads = []
for g, _ in grad_and_vars:
# Add 0 dimension to the gradients to represent the tower.
expanded_g = tf.expand_dims(g, 0)
# Append on a 'tower' dimension which we will average over below.
grads.append(expanded_g)
# Average over the 'tower' dimension.
grad = tf.concat(axis=0, values=grads)
grad = tf.reduce_mean(grad, 0)
# Keep in mind that the Variables are redundant because they are shared
# across towers. So .. we will just return the first tower's pointer to the Variable.
v = grad_and_vars[0][1]
grad_and_var = (grad, v)
average_grads.append(grad_and_var)
return average_grads
learning_rate = tf.train.exponential_decay(
learning_rate_placeholder,
global_step,
args.learning_rate_decay_epochs * args.epoch_size,
args.learning_rate_decay_factor,
staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
if args.optimizer == 'ADAGRAD':
opt = tf.train.AdagradOptimizer(learning_rate)
elif args.optimizer == 'ADADELTA':
opt = tf.train.AdadeltaOptimizer(learning_rate,
rho=0.9,
epsilon=1e-6)
elif args.optimizer == 'ADAM':
opt = tf.train.AdamOptimizer(learning_rate,
beta1=0.9,
beta2=0.999,
epsilon=0.1)
elif args.optimizer == 'RMSPROP':
opt = tf.train.RMSPropOptimizer(learning_rate,
decay=0.9,
momentum=0.9,
epsilon=1.0)
elif args.optimizer == 'MOM':
opt = tf.train.MomentumOptimizer(learning_rate,
0.9,
use_nesterov=True)
else:
raise ValueError('Invalid optimization algorithm')
tower_grads = []
with tf.variable_scope(tf.get_variable_scope()):
for i in range(2):
with tf.device('/gpu:%d' % i):
with tf.name_scope('%s_%d' % ('haha', i)) as scope:
total_loss, regularization_losses, embeddings = tower_loss(
scope, image_batch, label_batch,
args.keep_probability, phase_train_placeholder,
args.embedding_size, args.weight_decay,
nrof_classes, args.center_loss_factor,
args.center_loss_alfa)
# Reuse variables for the next tower.
tf.get_variable_scope().reuse_variables()
# Calculate the gradients for the batch of data on this CIFAR tower.
grads = opt.compute_gradients(total_loss)
# Keep track of the gradients across all towers.
tower_grads.append(grads)
# We must calculate the mean of each gradient. Note that this is the synchronization point across all towers.
grads = average_gradients(tower_grads)
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
if args.log_histograms:
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name, var)
# Add histograms for gradients.
if args.log_histograms:
for grad, var in grads:
if grad is not None:
tf.summary.histogram(var.op.name + '/gradients', grad)
# Track the moving averages of all trainable variables.
variable_averages = tf.train.ExponentialMovingAverage(
args.moving_average_decay, global_step)
variables_averages_op = variable_averages.apply(
tf.trainable_variables())
with tf.control_dependencies(
[apply_gradient_op, variables_averages_op]):
train_op = tf.no_op(name='train')
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
print('Running training')
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, epoch, image_list, label_list,
index_dequeue_op, enqueue_op, image_paths_placeholder,
labels_placeholder, learning_rate_placeholder,
phase_train_placeholder, batch_size_placeholder,
global_step, total_loss, train_op, summary_op,
summary_writer, regularization_losses,
args.learning_rate_schedule_file)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer,
model_dir, subdir, step)
# Evaluate on LFW
if args.lfw_dir:
evaluate(sess, enqueue_op, image_paths_placeholder,
labels_placeholder, phase_train_placeholder,
batch_size_placeholder, embeddings, label_batch,
lfw_paths, actual_issame, args.lfw_batch_size,
args.lfw_nrof_folds, log_dir, step,
summary_writer)
return model_dir
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
if args.use_split_dataset:
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(
dataset_tmp, args.min_nrof_images_per_class,
args.nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(
args.classifier_filename)
if (args.mode == 'TRAIN'):
# Train classifier
print('Training classifier')
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
############################################ data_visual(emb_array,class_names)
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
elif (args.mode == 'CLASSIFY'):
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s: %.3f' %
(i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
def main(argv=None):
align = align_dlib.AlignDlib(os.path.expanduser(FLAGS.dlib_face_predictor))
landmarkIndices = align_dlib.AlignDlib.OUTER_EYES_AND_NOSE
output_dir = os.path.expanduser(FLAGS.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
store_revision_info(src_path, output_dir, ' '.join(argv))
dataset = facenet.get_dataset(FLAGS.input_dir)
# Scale the image such that the face fills the frame when cropped to crop_size
scale = float(FLAGS.face_size) / FLAGS.image_size
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
for image_path in cls.image_paths:
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir, filename+'.png')
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim == 2:
img = facenet.to_rgb(img)
if FLAGS.use_new_alignment:
aligned = align.align_new(FLAGS.image_size, img, landmarkIndices=landmarkIndices,
skipMulti=True, scale=scale)
else:
aligned = align.align(FLAGS.image_size, img, landmarkIndices=landmarkIndices,
skipMulti=True, scale=scale)
if aligned is not None:
print(image_path)
misc.imsave(output_filename, aligned)
elif FLAGS.prealigned_path:
# Face detection failed. Use center crop from pre-aligned dataset
class_name = os.path.split(output_class_dir)[1]
image_path_without_ext = os.path.join(os.path.expanduser(FLAGS.prealigned_path),
class_name, filename)
# Find the extension of the image
exts = ('jpg', 'png', 'gif')
for ext in exts:
temp_path = image_path_without_ext + '.' + ext
image_path = ''
if os.path.exists(temp_path):
image_path = temp_path
break
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
scaled = misc.imresize(img, FLAGS.prealigned_scale, interp='bilinear')
sz1 = scaled.shape[1]/2
sz2 = FLAGS.image_size/2
cropped = scaled[(sz1-sz2):(sz1+sz2),(sz1-sz2):(sz1+sz2),:]
print(image_path)
misc.imsave(output_filename, cropped)
def train_classify(data_dir,
nrof_train_images_per_class,
classifier_filename,
mode='TRAIN',
use_split_dataset=False,
model="./model/20170511-185253.pb",
image_size=160,
batch_size=64,
min_nrof_images_per_class=1):
with tf.Graph().as_default():
with tf.Session() as sess:
if use_split_dataset == True:
dataset_tmp = facenet.get_dataset(data_dir)
train_set, test_set = split_dataset(
dataset_tmp, min_nrof_images_per_class,
nrof_train_images_per_class)
if (mode == 'TRAIN'):
dataset = train_set
elif (mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
t0 = time()
facenet.load_model(model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
t1 = time()
print('Model Loading : ', t1 - t0)
# Run forward pass to calculate embeddings
print('Calculating features for images')
t0 = time()
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * batch_size
end_index = min((i + 1) * batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(classifier_filename)
t1 = time()
print('Feature Extraction : ', t1 - t0)
if (mode == 'TRAIN'):
# Train classifier
print('Training classifier')
t0 = time()
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
'''model = RandomForestClassifier()
# Choose some parameter combinations to try
parameters = {'n_estimators': [4, 6, 9],
'max_features': ['log2', 'sqrt','auto'],
'criterion': ['entropy', 'gini'],
'max_depth': [2, 3, 5, 10],
'min_samples_split': [2, 3, 5],
'min_samples_leaf': [1,5,8]
}
# Type of scoring used to compare parameter combinations
acc_scorer = make_scorer(accuracy_score)
# Run the grid search
grid_obj = GridSearchCV(model, parameters, scoring=acc_scorer)
grid_obj = grid_obj.fit(emb_array, labels)
# Set the clf to the best combination of parameters
model = grid_obj.best_estimator_
# Fit the best algorithm to the data.
model.fit(emb_array, labels)'''
t1 = time()
print('Training Time : ', t1 - t0)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
elif (mode == 'CLASSIFY'):
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
class_names.append('Unknown')
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
#print(best_class_indices)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
#print(best_class_probabilities)
for i in range(len(best_class_indices)):
if best_class_probabilities[i] > 0.300:
print('%4d %s: %.3f' %
(i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
else:
print(
'%4d %s: %.3f' %
(i, class_names[-1], best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
def main(args):
network = importlib.import_module(args.model_def, 'inference')
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
if args.pretrained_model:
print('Pre-trained model: %s' % os.path.expanduser(args.pretrained_model))
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,3), name='image_paths')
labels_placeholder = tf.placeholder(tf.int64, shape=(None,3), name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(3,), (3,)],
shared_name=None, name=None)
enqueue_op = input_queue.enqueue_many([image_paths_placeholder, labels_placeholder])
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unpack(filenames):
file_contents = tf.read_file(filename)
image = tf.image.decode_png(file_contents)
if args.random_crop:
image = tf.random_crop(image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
image_batch, labels_batch = tf.train.batch_join(
images_and_labels, batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()], enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, weight_decay=args.weight_decay)
pre_embeddings = slim.fully_connected(prelogits, args.embedding_size, activation_fn=None, scope='Embeddings', reuse=False)
#embedding_size = 1792
embeddings = tf.nn.l2_normalize(pre_embeddings, 1, 1e-10, name='embeddings')
# Split embeddings into anchor, positive and negative and calculate triplet loss
anchor, positive, negative = tf.unpack(tf.reshape(embeddings, [-1,3,args.embedding_size]), 3, 1)
triplet_loss = facenet.triplet_loss(anchor, positive, negative, args.alpha)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([triplet_loss] + regularization_losses, name='total_loss')
# Create list with variables to restore
restore_vars = []
update_gradient_vars = []
if args.pretrained_model:
update_gradient_vars = tf.global_variables()
for var in tf.global_variables():
if not 'Embeddings/' in var.op.name:
restore_vars.append(var)
#else:
#update_gradient_vars.append(var)
else:
restore_vars = tf.global_variables()
update_gradient_vars = tf.global_variables()
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, update_gradient_vars)
# Create a saver
restore_saver = tf.train.Saver(restore_vars)
saver = tf.train.Saver(tf.global_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# Initialize variables
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
tf.train.start_queue_runners(sess=sess)
with sess.as_default():
if args.pretrained_model:
print('Restoring pretrained model: %s' % args.pretrained_model)
restore_saver.restore(sess, os.path.expanduser(args.pretrained_model))
# Training and validation loop
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, train_set, epoch, image_paths_placeholder, labels_placeholder, labels_batch,
batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op, input_queue, global_step,
embeddings, total_loss, train_op, summary_op, summary_writer, args.learning_rate_schedule_file,
args.embedding_size, anchor, positive, negative, triplet_loss)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step)
# Evaluate on LFW
if args.lfw_dir:
evaluate(sess, lfw_paths, embeddings, labels_batch, image_paths_placeholder, labels_placeholder,
batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op, actual_issame, args.batch_size,
args.seed, args.lfw_nrof_folds, log_dir, step, summary_writer, args.embedding_size)
return model_dir
def main(argv=None): # pylint: disable=unused-argument
if FLAGS.model_name:
subdir = FLAGS.model_name
preload_model = True
else:
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
preload_model = False
log_dir = os.path.join(os.path.expanduser(FLAGS.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.mkdir(log_dir)
model_dir = os.path.join(os.path.expanduser(FLAGS.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.mkdir(model_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(argv))
np.random.seed(seed=FLAGS.seed)
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, validation_set = facenet.split_dataset(dataset, FLAGS.train_set_fraction, FLAGS.split_mode)
print('Model directory: %s' % model_dir)
with tf.Graph().as_default():
tf.set_random_seed(FLAGS.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(None, FLAGS.image_size, FLAGS.image_size, 3), name='input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
embeddings = network.inference(images_placeholder, FLAGS.pool_type, FLAGS.use_lrn,
FLAGS.keep_probability, phase_train=phase_train_placeholder)
# Split example embeddings into anchor, positive and negative
anchor, positive, negative = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(anchor, positive, negative, FLAGS.alpha)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, _ = facenet.train(loss, global_step, FLAGS.optimizer, FLAGS.learning_rate, FLAGS.moving_average_decay)
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=0)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
with sess.as_default():
if preload_model:
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Training and validation loop
for epoch in range(FLAGS.max_nrof_epochs):
# Train for one epoch
step = train(sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Store the state of the random number generator
rng_state = np.random.get_state()
# Test on validation set
np.random.seed(seed=FLAGS.seed)
validate(sess, validation_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, 'validation', summary_writer)
# Test on training set
np.random.seed(seed=FLAGS.seed)
validate(sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, 'training', summary_writer)
# Restore state of the random number generator
np.random.set_state(rng_state)
if (epoch % FLAGS.checkpoint_period == 0) or (epoch==FLAGS.max_nrof_epochs-1):
# Save the model checkpoint
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def main(args):
align = align_dlib.AlignDlib(os.path.expanduser(args.dlib_face_predictor))
landmarkIndices = align_dlib.AlignDlib.OUTER_EYES_AND_NOSE
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
dataset = facenet.get_dataset(args.input_dir)
random.shuffle(dataset)
# Scale the image such that the face fills the frame when cropped to crop_size
scale = float(args.face_size) / args.image_size
nrof_images_total = 0
nrof_prealigned_images = 0
nrof_successfully_aligned = 0
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
random.shuffle(cls.image_paths)
for image_path in cls.image_paths:
nrof_images_total += 1
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir, filename+'.png')
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim == 2:
img = facenet.to_rgb(img)
if args.use_center_crop:
scaled = misc.imresize(img, args.prealigned_scale, interp='bilinear')
sz1 = scaled.shape[1]/2
sz2 = args.image_size/2
aligned = scaled[(sz1-sz2):(sz1+sz2),(sz1-sz2):(sz1+sz2),:]
else:
aligned = align.align(args.image_size, img, landmarkIndices=landmarkIndices,
skipMulti=False, scale=scale)
if aligned is not None:
print(image_path)
nrof_successfully_aligned += 1
misc.imsave(output_filename, aligned)
elif args.prealigned_dir:
# Face detection failed. Use center crop from pre-aligned dataset
class_name = os.path.split(output_class_dir)[1]
image_path_without_ext = os.path.join(os.path.expanduser(args.prealigned_dir),
class_name, filename)
# Find the extension of the image
exts = ('jpg', 'png')
for ext in exts:
temp_path = image_path_without_ext + '.' + ext
image_path = ''
if os.path.exists(temp_path):
image_path = temp_path
break
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
scaled = misc.imresize(img, args.prealigned_scale, interp='bilinear')
sz1 = scaled.shape[1]/2
sz2 = args.image_size/2
cropped = scaled[(sz1-sz2):(sz1+sz2),(sz1-sz2):(sz1+sz2),:]
print(image_path)
nrof_prealigned_images += 1
misc.imsave(output_filename, cropped)
else:
print('Unable to align "%s"' % image_path)
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' % nrof_successfully_aligned)
print('Number of pre-aligned images: %d' % nrof_prealigned_images)
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
emb_file = 'embeddings.pkl'
# Extract embeddings in trainset
if (args.mode == 'EXTRACT'):
np.random.seed(seed=666)
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
with open(emb_file, 'wb') as outfile:
pickle.dump((emb_array, labels, paths), outfile)
print('Embeddings save to file "%s"' % emb_file)
# Perform compare task
else:
# Load embeddings
print('Loading embeddings')
with open(emb_file, 'rb') as infile:
emb_array, labels, paths = pickle.load(infile)
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
images = load_and_align_data(args.image_files, args.image_size)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Run forward pass to calculate embeddings
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb = sess.run(embeddings, feed_dict=feed_dict)
nrof_images = len(args.image_files)
print('Images and embeddings:')
for i in range(nrof_images):
min_result = min_distance(emb[i], emb_array)
min_result_label = labels[min_result]
min_result_path = paths[min_result]
print(
'Compared image: %s, compared result: %s, label: %s, path: %s'
% (args.image_files[i], min_result, min_result_label,
min_result_path))
def main(args):
#导入模型
network = importlib.import_module(args.model_def)
#为本次运行新建日志目录与模型目录
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(
log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
#保存输入参数信息
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir,
'arguments.txt'))
#保存git相关信息
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
#获取数据集
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
#pre-trained model 路径
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
if args.pretrained_model:
print('Pre-trained model: %s' %
os.path.expanduser(args.pretrained_model))
#lfw测试集
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(
os.path.expanduser(args.lfw_dir), pairs)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
#创建各种placeholder
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32,
name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
#使用了三元组损失，输入需要3张图片
image_paths_placeholder = tf.placeholder(tf.string,
shape=(None, 3),
name='image_paths')
labels_placeholder = tf.placeholder(tf.int64,
shape=(None, 3),
name='labels')
#数据集准备
input_queue = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(3, ), (3, )],
shared_name=None,
name=None)
#文件入队操作
enqueue_op = input_queue.enqueue_many(
[image_paths_placeholder, labels_placeholder])
#读取队列数据，经过一系列转换（读取图片、切片、水平镜像、reshape）
#结果是[images,label],image.shape(3,160,160,3),label.shape (3,)
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unstack(filenames):
file_contents = tf.read_file(filename)
image = tf.image.decode_image(file_contents, channels=3)
if args.random_crop:
image = tf.random_crop(
image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(
image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
# 由于 enqueue_many=True
# 因此输入队列 images_and_labels 中的每个元素，即[images, label]也会根据axis=0的切分为多条数据
# image_batch 的 shape 为 (batch_size, image_size, image_size, 3)
# labels_batch 的 shape 为 (batch_size)
image_batch, labels_batch = tf.train.batch_join(
images_and_labels,
batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()],
enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
labels_batch = tf.identity(labels_batch, 'label_batch')
# 将图片转换为长度为128的向量，并进行l2 normalize操作
# Build the inference graph
#prelogits是最后一层的输出
prelogits, _ = network.inference(
image_batch,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
#对最后的输出进行标准化，得到该图像的embedding
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Split embeddings into anchor, positive and negative and calculate triplet loss
#将embedding分成三个部分，anchor，positive，negative
# 获取triplet输入数据，并计算损失函数
anchor, positive, negative = tf.unstack(
tf.reshape(embeddings, [-1, 3, args.embedding_size]), 3, 1)
#根据上面三个值计算三元组损失
triplet_loss = facenet.triplet_loss(anchor, positive, negative,
args.alpha)
#定义优化方法tf.train.exponential_decay 将指数衰减应用到学习率上 每decay_steps步更新学习速率
#获取学习率
learning_rate = tf.train.exponential_decay(
learning_rate_placeholder,
global_step,
args.learning_rate_decay_epochs * args.epoch_size,
args.learning_rate_decay_factor,
staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the total losses
#加入正则化损失
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
#整体损失=正则化损失+三元组损失
total_loss = tf.add_n([triplet_loss] + regularization_losses,
name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
#用上述定义的优化方法和loss进行优化
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay,
tf.global_variables())
# Create a saver
# saver summary相关
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
# 创建Session并进行变量初始化
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# Initialize variables
sess.run(tf.global_variables_initializer(),
feed_dict={phase_train_placeholder: True})
sess.run(tf.local_variables_initializer(),
feed_dict={phase_train_placeholder: True})
# # 运行输入数据队列，并获取FileWriter
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
# 导入 pre-trained model
if args.pretrained_model:
print('Restoring pretrained model: %s' % args.pretrained_model)
# saver.restore(sess, os.path.expanduser(args.pretrained_model))
facenet.load_model(args.pretrained_model)
# Training and validation loop
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
# 构建一个epoch的数据并训练
train(args, sess, train_set, epoch, image_paths_placeholder,
labels_placeholder, labels_batch, batch_size_placeholder,
learning_rate_placeholder, phase_train_placeholder,
enqueue_op, input_queue, global_step, embeddings,
total_loss, train_op, summary_op, summary_writer,
args.learning_rate_schedule_file, args.embedding_size,
anchor, positive, negative, triplet_loss)
# Save variables and the metagraph if it doesn't exist already
# 保存模型
save_variables_and_metagraph(sess, saver, summary_writer,
model_dir, subdir, step)
# Evaluate on LFW
# 在 lfw 上验证模型性能
if args.lfw_dir:
evaluate(sess, lfw_paths, embeddings, labels_batch,
image_paths_placeholder, labels_placeholder,
batch_size_placeholder, learning_rate_placeholder,
phase_train_placeholder, enqueue_op,
actual_issame, args.batch_size,
args.lfw_nrof_folds, log_dir, step,
summary_writer, args.embedding_size)
return model_dir
def main(args):
img_mean = np.array([134.10714722, 102.52040863, 87.15436554])
img_stddev = np.sqrt(np.array([3941.30175781, 2856.94287109, 2519.35791016]))
vae_def = importlib.import_module(args.vae_def)
vae = vae_def.Vae(args.latent_var_size)
gen_image_size = vae.get_image_size()
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
log_file_name = os.path.join(model_dir, 'logs.h5')
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(model_dir, 'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, model_dir, ' '.join(sys.argv))
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
train_set = facenet.get_dataset(args.data_dir)
image_list, _ = facenet.get_image_paths_and_labels(train_set)
# Create the input queue
input_queue = tf.train.string_input_producer(image_list, shuffle=True)
nrof_preprocess_threads = 4
image_per_thread = []
for _ in range(nrof_preprocess_threads):
file_contents = tf.read_file(input_queue.dequeue())
image = tf.image.decode_image(file_contents, channels=3)
image = tf.image.resize_image_with_crop_or_pad(image, args.input_image_size, args.input_image_size)
image.set_shape((args.input_image_size, args.input_image_size, 3))
image = tf.cast(image, tf.float32)
#pylint: disable=no-member
image_per_thread.append([image])
images = tf.train.batch_join(
image_per_thread, batch_size=args.batch_size,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=False)
# Normalize
images_norm = (images-img_mean) / img_stddev
# Resize to appropriate size for the encoder
images_norm_resize = tf.image.resize_images(images_norm, (gen_image_size,gen_image_size))
# Create encoder network
mean, log_variance = vae.encoder(images_norm_resize, True)
epsilon = tf.random_normal((tf.shape(mean)[0], args.latent_var_size))
std = tf.exp(log_variance/2)
latent_var = mean + epsilon * std
# Create decoder network
reconstructed_norm = vae.decoder(latent_var, True)
# Un-normalize
reconstructed = (reconstructed_norm*img_stddev) + img_mean
# Create reconstruction loss
if args.reconstruction_loss_type=='PLAIN':
images_resize = tf.image.resize_images(images, (gen_image_size,gen_image_size))
reconstruction_loss = tf.reduce_mean(tf.reduce_sum(tf.pow(images_resize - reconstructed,2)))
elif args.reconstruction_loss_type=='PERCEPTUAL':
network = importlib.import_module(args.model_def)
reconstructed_norm_resize = tf.image.resize_images(reconstructed_norm, (args.input_image_size,args.input_image_size))
# Stack images from both the input batch and the reconstructed batch in a new tensor
shp = [-1] + images_norm.get_shape().as_list()[1:]
input_images = tf.reshape(tf.stack([images_norm, reconstructed_norm_resize], axis=0), shp)
_, end_points = network.inference(input_images, 1.0,
phase_train=False, bottleneck_layer_size=128, weight_decay=0.0)
# Get a list of feature names to use for loss terms
feature_names = args.loss_features.replace(' ', '').split(',')
# Calculate L2 loss between original and reconstructed images in feature space
reconstruction_loss_list = []
for feature_name in feature_names:
feature_flat = slim.flatten(end_points[feature_name])
image_feature, reconstructed_feature = tf.unstack(tf.reshape(feature_flat, [2,args.batch_size,-1]), num=2, axis=0)
reconstruction_loss = tf.reduce_mean(tf.reduce_sum(tf.pow(image_feature-reconstructed_feature, 2)), name=feature_name+'_loss')
reconstruction_loss_list.append(reconstruction_loss)
# Sum up the losses in for the different features
reconstruction_loss = tf.add_n(reconstruction_loss_list, 'reconstruction_loss')
else:
pass
# Create KL divergence loss
kl_loss = kl_divergence_loss(mean, log_variance)
kl_loss_mean = tf.reduce_mean(kl_loss)
total_loss = args.alfa*kl_loss_mean + args.beta*reconstruction_loss
learning_rate = tf.train.exponential_decay(args.initial_learning_rate, global_step,
args.learning_rate_decay_steps, args.learning_rate_decay_factor, staircase=True)
# Calculate gradients and make sure not to include parameters for the perceptual loss model
opt = tf.train.AdamOptimizer(learning_rate)
grads = opt.compute_gradients(total_loss, var_list=get_variables_to_train())
# Apply gradients
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
with tf.control_dependencies([apply_gradient_op]):
train_op = tf.no_op(name='train')
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
facenet_saver = tf.train.Saver(get_facenet_variables_to_restore())
# Start running operations on the Graph
gpu_memory_fraction = 1.0
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if args.reconstruction_loss_type=='PERCEPTUAL':
if not args.pretrained_model:
raise ValueError('A pretrained model must be specified when using perceptual loss')
pretrained_model_exp = os.path.expanduser(args.pretrained_model)
print('Restoring pretrained model: %s' % pretrained_model_exp)
facenet_saver.restore(sess, pretrained_model_exp)
log = {
'total_loss': np.zeros((0,), np.float),
'reconstruction_loss': np.zeros((0,), np.float),
'kl_loss': np.zeros((0,), np.float),
'learning_rate': np.zeros((0,), np.float),
}
step = 0
print('Running training')
while step < args.max_nrof_steps:
start_time = time.time()
step += 1
save_state = step>0 and (step % args.save_every_n_steps==0 or step==args.max_nrof_steps)
if save_state:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_, rec_ = sess.run(
[train_op, reconstruction_loss, kl_loss_mean, total_loss, learning_rate, reconstructed])
img = facenet.put_images_on_grid(rec_, shape=(16,8))
misc.imsave(os.path.join(model_dir, 'reconstructed_%06d.png' % step), img)
else:
_, reconstruction_loss_, kl_loss_mean_, total_loss_, learning_rate_ = sess.run(
[train_op, reconstruction_loss, kl_loss_mean, total_loss, learning_rate])
log['total_loss'] = np.append(log['total_loss'], total_loss_)
log['reconstruction_loss'] = np.append(log['reconstruction_loss'], reconstruction_loss_)
log['kl_loss'] = np.append(log['kl_loss'], kl_loss_mean_)
log['learning_rate'] = np.append(log['learning_rate'], learning_rate_)
duration = time.time() - start_time
print('Step: %d \tTime: %.3f \trec_loss: %.3f \tkl_loss: %.3f \ttotal_loss: %.3f' % (step, duration, reconstruction_loss_, kl_loss_mean_, total_loss_))
if save_state:
print('Saving checkpoint file')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step, write_meta_graph=False)
print('Saving log')
with h5py.File(log_file_name, 'w') as f:
for key, value in log.iteritems():
f.create_dataset(key, data=value)
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
dataset = facenet.get_dataset(args.data_dir)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
start_time = time.time()
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
duration = time.time() - start_time
print('Calculating features Time %.3f' % duration)
'''
# save emb_array and labels
scipy.io.savemat(args.save_path,{'emb_array':emb_array,'labels':labels})
print('Embeddings data saved')
'''
if (args.mode == 'SVM'):
classifier_filename_exp = os.path.expanduser(
args.classifier_filename_svm)
start_time = time.time()
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
duration = time.time() - start_time
print('classifier Time %.3f' % duration)
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
elif (args.mode == 'FNN'):
start_time = time.time()
#load meta graph and restore weights
saver = tf.train.import_meta_graph(classifier_filename_fnn)
saver.restore(
sess, tf.train.latest_checkpoint(checkpoint_filename_fnn))
# Get input and output tensors
graph = tf.get_default_graph()
x = graph.get_tensor_by_name("input/x-input:0")
keep_prob = graph.get_tensor_by_name("dropout/keep_prob:0")
y_hat = graph.get_tensor_by_name("output/activation:0")
feed_dict = {x: emb_array, keep_prob: 1.0}
predictions = tf.argmax(y_hat, 1)
best_class_indices = sess.run(predictions, feed_dict=feed_dict)
duration = time.time() - start_time
print('classifier Time %.3f' % duration)
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
def main(args):
network = importlib.import_module(args.model_def, 'inference')
if args.model_name:
subdir = args.model_name
preload_model = True
else:
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
preload_model = False
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(
log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir),
pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32,
shape=(None, args.image_size,
args.image_size, 3),
name='input')
# Placeholder for the learning rate
labels_placeholder = tf.placeholder(tf.int64, name='labels')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32,
name='learing_rate')
# Build the inference graph
logits1, logits2 = network.inference(
images_placeholder, [128, len(train_set)],
args.keep_probability,
phase_train=phase_train_placeholder,
weight_decay=args.weight_decay)
# Split example embeddings into anchor, positive and negative and calculate triplet loss
embeddings = tf.nn.l2_normalize(logits1, 1, 1e-10, name='embeddings')
anchor, positive, negative = tf.split(0, 3, embeddings)
triplet_loss = facenet.triplet_loss(anchor, positive, negative,
args.alpha)
learning_rate = tf.train.exponential_decay(
learning_rate_placeholder,
global_step,
args.learning_rate_decay_epochs * args.epoch_size,
args.learning_rate_decay_factor,
staircase=True)
tf.scalar_summary('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch.
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits2, labels_placeholder, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy,
name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# Calculate the total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
total_triplet_loss = tf.add_n([triplet_loss] + regularization_losses,
name='total_triplet_loss')
total_xent_loss = tf.add_n([cross_entropy_mean] +
regularization_losses,
name='total_xent_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
triplet_loss_train_op = facenet.train('tripletloss_',
total_triplet_loss, global_step,
args.optimizer, learning_rate,
args.moving_average_decay)
xent_loss_train_op = facenet.train('xent_', total_xent_loss,
global_step, args.optimizer,
learning_rate,
args.moving_average_decay)
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=0)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
sess.run(init)
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
with sess.as_default():
if preload_model:
ckpt = tf.train.get_checkpoint_state(model_dir)
#pylint: disable=maybe-no-member
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Training and validation loop
epoch = 0
while epoch < args.max_nrof_epochs:
epoch = sess.run(global_step,
feed_dict=None) // args.epoch_size
# Train for one epoch
if args.loss_type == 'CLASSIFIER':
step = train_classifier(
args, sess, train_set, epoch, images_placeholder,
labels_placeholder, phase_train_placeholder,
learning_rate_placeholder, global_step,
total_xent_loss, xent_loss_train_op, summary_op,
summary_writer, regularization_losses)
elif args.loss_type == 'TRIPLETLOSS':
step = train_triplet_loss(
args, sess, train_set, epoch, images_placeholder,
labels_placeholder, phase_train_placeholder,
learning_rate_placeholder, global_step, embeddings,
total_triplet_loss, triplet_loss_train_op, summary_op,
summary_writer)
else:
pass
if args.lfw_dir:
_, _, accuracy, val, val_std, far = lfw.validate(
sess,
paths,
actual_issame,
args.seed,
args.batch_size,
images_placeholder,
phase_train_placeholder,
embeddings,
nrof_folds=args.lfw_nrof_folds)
print('Accuracy: %1.3f+-%1.3f' %
(np.mean(accuracy), np.std(accuracy)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' %
(val, val_std, far))
# Add validation loss and accuracy to summary
summary = tf.Summary()
#pylint: disable=maybe-no-member
summary.value.add(tag='lfw/accuracy',
simple_value=np.mean(accuracy))
summary.value.add(tag='lfw/val_rate', simple_value=val)
summary_writer.add_summary(summary, step)
if (epoch % args.checkpoint_period
== 0) or (epoch == args.max_nrof_epochs - 1):
# Save the model checkpoint
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
return model_dir
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(
args.classifier_filename)
if (args.mode == 'TRAIN'):
neighbours_classifier = NearestNeighbors(
n_neighbors=2, algorithm='ball_tree').fit(emb_array)
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((neighbours_classifier), outfile)
print(
"Done fitting the nearest neighbour classifier. Saved in ",
classifier_filename_exp)
elif (args.mode == 'CLASSIFY'):
with open(classifier_filename_exp, 'rb') as infile:
neighbours_classifier = pickle.load(infile)
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
distances, indices = neighbours_classifier.kneighbors(
emb_array)
print(distances)
print(indices)
def main(args):
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
dataset = facenet.get_dataset(args.input_dir)
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = align.detect_face.create_mtcnn(sess, '../../data/')
minsize = 20 # minimum size of face
threshold = [ 0.6, 0.7, 0.7 ] # three steps's threshold
factor = 0.709 # scale factor
# Add a random key to the filename to allow alignment using multiple processes
random_key = np.random.randint(0, high=99999)
bounding_boxes_filename = os.path.join(output_dir, 'bounding_boxes_%05d.txt' % random_key)
with open(bounding_boxes_filename, "w") as text_file:
nrof_images_total = 0
nrof_successfully_aligned = 0
if args.random_order:
random.shuffle(dataset)
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
if args.random_order:
random.shuffle(cls.image_paths)
for image_path in cls.image_paths:
nrof_images_total += 1
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir, filename+'.png')
print(image_path)
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim<2:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
continue
if img.ndim == 2:
img = facenet.to_rgb(img)
img = img[:,:,0:3]
bounding_boxes, _ = align.detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces>0:
det = bounding_boxes[:,0:4]
img_size = np.asarray(img.shape)[0:2]
if nrof_faces>1:
bounding_box_size = (det[:,2]-det[:,0])*(det[:,3]-det[:,1])
img_center = img_size / 2
offsets = np.vstack([ (det[:,0]+det[:,2])/2-img_center[1], (det[:,1]+det[:,3])/2-img_center[0] ])
offset_dist_squared = np.sum(np.power(offsets,2.0),0)
index = np.argmax(bounding_box_size-offset_dist_squared*2.0) # some extra weight on the centering
det = det[index,:]
det = np.squeeze(det)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0]-args.margin/2, 0)
bb[1] = np.maximum(det[1]-args.margin/2, 0)
bb[2] = np.minimum(det[2]+args.margin/2, img_size[1])
bb[3] = np.minimum(det[3]+args.margin/2, img_size[0])
cropped = img[bb[1]:bb[3],bb[0]:bb[2],:]
scaled = misc.imresize(cropped, (args.image_size, args.image_size), interp='bilinear')
nrof_successfully_aligned += 1
misc.imsave(output_filename, scaled)
text_file.write('%s %d %d %d %d\n' % (output_filename, bb[0], bb[1], bb[2], bb[3]))
else:
print('Unable to align "%s"' % image_path)
text_file.write('%s\n' % (output_filename))
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' % nrof_successfully_aligned)
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
dataset = facenet.get_dataset(args.data_dir)
# get dataset name from the data_dir
dataset_name = args.data_dir.split('/')
#print(len(dataset_name))
dataset_name = dataset_name[len(dataset_name) - 1]
#print(dataset_name)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
with open(dataset_name + ".paths.json", "w") as outfile:
json.dump(paths, outfile, indent=4)
with open(dataset_name + ".labels.json", "w") as outfile:
json.dump(labels, outfile, indent=4)
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
# save the features to h5 file
h5f = h5py.File(dataset_name + '.h5.facenet', 'w')
h5f.create_dataset('/dataset', data=emb_array)
h5f.close()
def main(args):
network = importlib.import_module(args.model_def, 'inference')
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
# 创建模型文件夹
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
if args.baihe_pack_file:
print('load baihe dataset')
lfw_paths, actual_issame = msgpack_numpy.load(open(args.baihe_pack_file))
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
# 迭代轮数, 不同的轮数可以使用不同的学习率
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
# Read data and apply label preserving distortions
image_batch, label_batch = facenet.read_and_augment_data(image_list, label_list, args.image_size,
args.batch_size, args.max_nrof_epochs, args.random_crop, args.random_flip, args.random_rotate,
args.nrof_preprocess_threads)
print('Total number of classes: %d' % nrof_classes)
print('Total number of examples: %d' % len(image_list))
print('Building training graph')
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
# Build the inference graph, 返回的是网络结构
prelogits, _ = network.inference(image_batch, args.keep_probability, phase_train=True,
weight_decay=args.weight_decay)
# 初始化采用截断的正态分布噪声, 标准差为0.1
# tf.truncated_normal_initializer(stddev=0.1)
logits = slim.fully_connected(prelogits, len(train_set), activation_fn=None,
weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits', reuse=False)
# Add DeCov regularization loss
if args.decov_loss_factor > 0.0:
logits_decov_loss = facenet.decov_loss(logits) * args.decov_loss_factor
# 将decov_loss加入到名字为tf.GraphKeys.REGULARIZATION_LOSSES的集合当中来
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, logits_decov_loss)
# Add center loss (center_loss作为一个正则项加入到collections)
if args.center_loss_factor > 0.0:
prelogits_center_loss, _ = facenet.center_loss(prelogits, label_batch, args.center_loss_alfa, nrof_classes)
# 将center加入到名字为tf.GraphKeys.REGULARIZATION_LOSSES的集合当中来
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor)
# 对学习率进行指数衰退
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.scalar_summary('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch
# 将softmax和交叉熵一起做,得到最后的损失函数,提高效率
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits, label_batch, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# Calculate the total losses
# 获取正则loss
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, tf.all_variables(), args.log_histograms)
# Evaluation
print('Building evaluation graph')
lfw_label_list = range(0, len(lfw_paths))
assert (len(lfw_paths) % args.lfw_batch_size == 0), \
"The number of images in the LFW test set need to be divisible by the lfw_batch_size"
eval_image_batch, eval_label_batch = facenet.read_and_augment_data(lfw_paths, lfw_label_list, args.image_size,
args.lfw_batch_size, None, False, False,
False, args.nrof_preprocess_threads,
shuffle=False)
# Node for input images
eval_image_batch.set_shape((None, args.image_size, args.image_size, 3))
eval_image_batch = tf.identity(eval_image_batch, name='input')
eval_prelogits, _ = network.inference(eval_image_batch, 1.0,
phase_train=False, weight_decay=0.0, reuse=True)
eval_embeddings = tf.nn.l2_normalize(eval_prelogits, 1, 1e-10, name='embeddings')
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=10)
# saver = tf.train.Saver(tf.global_variables(), max_to_keep=10)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
# sess.run(tf.global_variables_initializer())
# sess.run(tf.local_variables_initializer())
sess.run(tf.initialize_all_variables())
sess.run(tf.initialize_local_variables())
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
tf.train.start_queue_runners(sess=sess)
# 将队列runner启动，队列就开始运行，返回启动的线程
# 注意input_queue是先入列，再出列，由于入列的时候输入是place holder，因此到后的线程的时候，会阻塞，
# 直到下train中sess run （enqueue_op）的时候， 会向队列中载入值，后面的出列才有对象，才在各自的队列中开始执行
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
print('Running training')
epoch = 0
while epoch < args.max_nrof_epochs:
try:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, epoch, learning_rate_placeholder, global_step, total_loss, train_op, summary_op,
summary_writer, regularization_losses, args.learning_rate_schedule_file)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step)
# Evaluate on LFW
if args.lfw_dir:
evaluate(sess, eval_embeddings, eval_label_batch, actual_issame, args.lfw_batch_size, args.seed,
args.lfw_nrof_folds, log_dir, step, summary_writer)
# Evaluate on baihe_data
if args.baihe_pack_file:
evaluate(sess, eval_embeddings, eval_label_batch, actual_issame, args.lfw_batch_size, args.seed,
args.lfw_nrof_folds, log_dir, step, summary_writer)
except:
traceback.print_exc()
continue
return model_dir
def main(args):
network = importlib.import_module(args.model_def)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(
log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(
model_dir): # Create the models directory if it doesn't exist
os.makedirs(model_dir)
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir,
'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
train_set = facenet.get_dataset(args.data_dir)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
if args.pretrained_model:
print('Pre-trained models: %s' %
os.path.expanduser(args.pretrained_model))
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(
os.path.expanduser(args.lfw_dir), pairs)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32,
name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string,
shape=(None, 3),
name='image_paths')
labels_placeholder = tf.placeholder(tf.int64,
shape=(None, 3),
name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(3, ), (3, )],
shared_name=None,
name=None)
enqueue_op = input_queue.enqueue_many(
[image_paths_placeholder, labels_placeholder])
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unstack(filenames):
file_contents = tf.read_file(filename)
image = tf.image.decode_image(file_contents, channels=3)
if args.random_crop:
image = tf.random_crop(
image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(
image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
image_batch, labels_batch = tf.train.batch_join(
images_and_labels,
batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()],
enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
labels_batch = tf.identity(labels_batch, 'label_batch')
# Build the inference graph
prelogits, _ = network.inference(
image_batch,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Split embeddings into anchor, positive and negative and calculate triplet loss
anchor, positive, negative = tf.unstack(
tf.reshape(embeddings, [-1, 3, args.embedding_size]), 3, 1)
triplet_loss = facenet.triplet_loss(anchor, positive, negative,
args.alpha)
learning_rate = tf.train.exponential_decay(
learning_rate_placeholder,
global_step,
args.learning_rate_decay_epochs * args.epoch_size,
args.learning_rate_decay_factor,
staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([triplet_loss] + regularization_losses,
name='total_loss')
# Build a Graph that trains the models with one batch of examples and updates the models parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay,
tf.global_variables())
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# Initialize variables
sess.run(tf.global_variables_initializer(),
feed_dict={phase_train_placeholder: True})
sess.run(tf.local_variables_initializer(),
feed_dict={phase_train_placeholder: True})
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if args.pretrained_model:
print('Restoring pretrained models: %s' %
args.pretrained_model)
saver.restore(sess, os.path.expanduser(args.pretrained_model))
# Training and validation loop
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, train_set, epoch, image_paths_placeholder,
labels_placeholder, labels_batch, batch_size_placeholder,
learning_rate_placeholder, phase_train_placeholder,
enqueue_op, input_queue, global_step, embeddings,
total_loss, train_op, summary_op, summary_writer,
args.learning_rate_schedule_file, args.embedding_size,
anchor, positive, negative, triplet_loss)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer,
model_dir, subdir, step)
# Evaluate on LFW
if args.lfw_dir:
evaluate(sess, lfw_paths, embeddings, labels_batch,
image_paths_placeholder, labels_placeholder,
batch_size_placeholder, learning_rate_placeholder,
phase_train_placeholder, enqueue_op,
actual_issame, args.batch_size,
args.lfw_nrof_folds, log_dir, step,
summary_writer, args.embedding_size)
return model_dir
def main(args):
network = importlib.import_module(args.model_def)
image_size = (args.image_size, args.image_size)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
stat_file_name = os.path.join(log_dir, 'stat.h5')
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir, 'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
random.seed(args.seed)
dataset = facenet.get_dataset(args.data_dir)
if args.filter_filename:
dataset = filter_dataset(dataset, os.path.expanduser(args.filter_filename),
args.filter_percentile, args.filter_min_nrof_images_per_class)
if args.validation_set_split_ratio>0.0:
train_set, val_set = facenet.split_dataset(dataset, args.validation_set_split_ratio, args.min_nrof_val_images_per_class, 'SPLIT_IMAGES')
else:
train_set, val_set = dataset, []
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list)>0, 'The training set should not be empty'
val_image_list, val_label_list = facenet.get_image_paths_and_labels(val_set)
# Create a queue that produces indices into the image_list and label_list
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
index_queue = tf.train.range_input_producer(range_size, num_epochs=None,
shuffle=True, seed=None, capacity=32)
index_dequeue_op = index_queue.dequeue_many(args.batch_size*args.epoch_size, 'index_dequeue')
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,1), name='image_paths')
labels_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='labels')
control_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='control')
nrof_preprocess_threads = 4
input_queue = data_flow_ops.FIFOQueue(capacity=2000000,
dtypes=[tf.string, tf.int32, tf.int32],
shapes=[(1,), (1,), (1,)],
shared_name=None, name=None)
enqueue_op = input_queue.enqueue_many([image_paths_placeholder, labels_placeholder, control_placeholder], name='enqueue_op')
image_batch, label_batch = facenet.create_input_pipeline(input_queue, image_size, nrof_preprocess_threads, batch_size_placeholder)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
label_batch = tf.identity(label_batch, 'label_batch')
print('Number of classes in training set: %d' % nrof_classes)
print('Number of examples in training set: %d' % len(image_list))
print('Number of classes in validation set: %d' % len(val_set))
print('Number of examples in validation set: %d' % len(val_image_list))
print('Building training graph')
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
logits = slim.fully_connected(prelogits, len(train_set), activation_fn=None,
weights_initializer=slim.initializers.xavier_initializer(),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits', reuse=False)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Norm for the prelogits
eps = 1e-4
prelogits_norm = tf.reduce_mean(tf.norm(tf.abs(prelogits)+eps, ord=args.prelogits_norm_p, axis=1))
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_norm * args.prelogits_norm_loss_factor)
# Add center loss
prelogits_center_loss, _ = facenet.center_loss(prelogits, label_batch, args.center_loss_alfa, nrof_classes)
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch, logits=logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
correct_prediction = tf.cast(tf.equal(tf.argmax(logits, 1), tf.cast(label_batch, tf.int64)), tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, tf.global_variables(), args.log_histograms)
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
print('Running training')
nrof_steps = args.max_nrof_epochs*args.epoch_size
nrof_val_samples = int(math.ceil(args.max_nrof_epochs / args.validate_every_n_epochs)) # Validate every validate_every_n_epochs as well as in the last epoch
stat = {
'loss': np.zeros((nrof_steps,), np.float32),
'center_loss': np.zeros((nrof_steps,), np.float32),
'reg_loss': np.zeros((nrof_steps,), np.float32),
'xent_loss': np.zeros((nrof_steps,), np.float32),
'prelogits_norm': np.zeros((nrof_steps,), np.float32),
'accuracy': np.zeros((nrof_steps,), np.float32),
'val_loss': np.zeros((nrof_val_samples,), np.float32),
'val_xent_loss': np.zeros((nrof_val_samples,), np.float32),
'val_accuracy': np.zeros((nrof_val_samples,), np.float32),
'lfw_accuracy': np.zeros((args.max_nrof_epochs,), np.float32),
'lfw_valrate': np.zeros((args.max_nrof_epochs,), np.float32),
'learning_rate': np.zeros((args.max_nrof_epochs,), np.float32),
'time_train': np.zeros((args.max_nrof_epochs,), np.float32),
'time_validate': np.zeros((args.max_nrof_epochs,), np.float32),
'time_evaluate': np.zeros((args.max_nrof_epochs,), np.float32),
'prelogits_hist': np.zeros((args.max_nrof_epochs, 1000), np.float32),
}
for epoch in range(1,args.max_nrof_epochs+1):
step = sess.run(global_step, feed_dict=None)
# Train for one epoch
t = time.time()
cont = train(args, sess, epoch, image_list, label_list, index_dequeue_op, enqueue_op, image_paths_placeholder, labels_placeholder,
learning_rate_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder, global_step,
total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file,
stat, cross_entropy_mean, accuracy, learning_rate,
prelogits, prelogits_center_loss, args.random_rotate, args.random_crop, args.random_flip, prelogits_norm, args.prelogits_hist_max, args.use_fixed_image_standardization)
stat['time_train'][epoch-1] = time.time() - t
if not cont:
break
t = time.time()
if len(val_image_list)>0 and ((epoch-1) % args.validate_every_n_epochs == args.validate_every_n_epochs-1 or epoch==args.max_nrof_epochs):
validate(args, sess, epoch, val_image_list, val_label_list, enqueue_op, image_paths_placeholder, labels_placeholder, control_placeholder,
phase_train_placeholder, batch_size_placeholder,
stat, total_loss, regularization_losses, cross_entropy_mean, accuracy, args.validate_every_n_epochs, args.use_fixed_image_standardization)
stat['time_validate'][epoch-1] = time.time() - t
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, epoch)
# Evaluate on LFW
t = time.time()
if args.lfw_dir:
evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
embeddings, label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer, stat, epoch,
args.lfw_distance_metric, args.lfw_subtract_mean, args.lfw_use_flipped_images, args.use_fixed_image_standardization)
stat['time_evaluate'][epoch-1] = time.time() - t
print('Saving statistics')
with h5py.File(stat_file_name, 'w') as f:
for key, value in stat.iteritems():
f.create_dataset(key, data=value)
return model_dir
def main(args):
align = align_dlib.AlignDlib(os.path.expanduser(args.dlib_face_predictor))
landmarkIndices = align_dlib.AlignDlib.OUTER_EYES_AND_NOSE
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
src_path, _ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
dataset = facenet.get_dataset(args.input_dir)
random.shuffle(dataset)
# Scale the image such that the face fills the frame when cropped to crop_size
scale = float(args.face_size) / args.image_size
nrof_images_total = 0
nrof_prealigned_images = 0
nrof_successfully_aligned = 0
for cls in dataset:
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
random.shuffle(cls.image_paths)
for image_path in cls.image_paths:
nrof_images_total += 1
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir, filename + '.png')
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim == 2:
img = facenet.to_rgb(img)
if args.use_center_crop:
scaled = misc.imresize(img,
args.prealigned_scale,
interp='bilinear')
sz1 = scaled.shape[1] / 2
sz2 = args.image_size / 2
aligned = scaled[(sz1 - sz2):(sz1 + sz2),
(sz1 - sz2):(sz1 + sz2), :]
else:
aligned = align.align(args.image_size,
img,
landmarkIndices=landmarkIndices,
skipMulti=False,
scale=scale)
if aligned is not None:
print(image_path)
nrof_successfully_aligned += 1
misc.imsave(output_filename, aligned)
elif args.prealigned_dir:
# Face detection failed. Use center crop from pre-aligned dataset
class_name = os.path.split(output_class_dir)[1]
image_path_without_ext = os.path.join(
os.path.expanduser(args.prealigned_dir),
class_name, filename)
# Find the extension of the image
exts = ('jpg', 'png')
for ext in exts:
temp_path = image_path_without_ext + '.' + ext
image_path = ''
if os.path.exists(temp_path):
image_path = temp_path
break
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
scaled = misc.imresize(img,
args.prealigned_scale,
interp='bilinear')
sz1 = scaled.shape[1] / 2
sz2 = args.image_size / 2
cropped = scaled[(sz1 - sz2):(sz1 + sz2),
(sz1 - sz2):(sz1 + sz2), :]
print(image_path)
nrof_prealigned_images += 1
misc.imsave(output_filename, cropped)
else:
print('Unable to align "%s"' % image_path)
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' %
nrof_successfully_aligned)
print('Number of pre-aligned images: %d' % nrof_prealigned_images)
import tensorflow as tf
import numpy as np
import facenet
import os
import math
import pickle
from sklearn.svm import SVC
with tf.Graph().as_default():
with tf.Session() as sess:
datadir = './output/'
dataset = facenet.get_dataset(datadir)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
print('Loading feature extraction model')
modeldir = './models/facenet/20190310-055158'
facenet.load_model(modeldir)
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
import os
import argparse
import tensorflow as tf
import numpy as np
import facenet
import detect_face
import random
from time import sleep
output_dir_path = './faces'
output_dir = os.path.expanduser(output_dir_path)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
datadir = './raw_faces'
dataset = facenet.get_dataset(datadir)
print('Creating networks and loading parameters')
with tf.Graph().as_default():
#gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)
sess = tf.Session()
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, './data')
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 44
image_size = 182
# Add a random key to the filename to allow alignment using multiple processes
def main(args):
network = importlib.import_module(args.model_def)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
random.seed(args.seed)
train_set = facenet.get_dataset(args.data_dir)
if args.filter_filename:
train_set = filter_dataset(train_set, os.path.expanduser(args.filter_filename),
args.filter_percentile, args.filter_min_nrof_images_per_class)
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list)>0, 'The dataset should not be empty'
# Create a queue that produces indices into the image_list and label_list
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
index_queue = tf.train.range_input_producer(range_size, num_epochs=None,
shuffle=True, seed=None, capacity=32)
index_dequeue_op = index_queue.dequeue_many(args.batch_size*args.epoch_size, 'index_dequeue')
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,1), name='image_paths')
labels_placeholder = tf.placeholder(tf.int64, shape=(None,1), name='labels')
input_queue = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(1,), (1,)],
shared_name=None, name=None)
enqueue_op = input_queue.enqueue_many([image_paths_placeholder, labels_placeholder], name='enqueue_op')
nrof_preprocess_threads = 4
images_and_labels = []
for _ in range(nrof_preprocess_threads):
filenames, label = input_queue.dequeue()
images = []
for filename in tf.unstack(filenames):
file_contents = tf.read_file(filename)
image = tf.image.decode_png(file_contents)
if args.random_rotate:
image = tf.py_func(facenet.random_rotate_image, [image], tf.uint8)
if args.random_crop:
image = tf.random_crop(image, [args.image_size, args.image_size, 3])
else:
image = tf.image.resize_image_with_crop_or_pad(image, args.image_size, args.image_size)
if args.random_flip:
image = tf.image.random_flip_left_right(image)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
images.append(tf.image.per_image_standardization(image))
images_and_labels.append([images, label])
image_batch, label_batch = tf.train.batch_join(
images_and_labels, batch_size=batch_size_placeholder,
shapes=[(args.image_size, args.image_size, 3), ()], enqueue_many=True,
capacity=4 * nrof_preprocess_threads * args.batch_size,
allow_smaller_final_batch=True)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
label_batch = tf.identity(label_batch, 'label_batch')
print('Total number of classes: %d' % nrof_classes)
print('Total number of examples: %d' % len(image_list))
print('Building training graph')
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
logits = slim.fully_connected(prelogits, len(train_set), activation_fn=None,
weights_initializer=tf.truncated_normal_initializer(stddev=0.1),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits', reuse=False)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Add center loss
if args.center_loss_factor>0.0:
prelogits_center_loss, _ = facenet.center_loss(prelogits, label_batch, args.center_loss_alfa, nrof_classes)
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch, logits=logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, tf.global_variables(), args.log_histograms)
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
print('Running training')
epoch = 0
while epoch < args.max_nrof_epochs:
step = sess.run(global_step, feed_dict=None)
epoch = step // args.epoch_size
# Train for one epoch
train(args, sess, epoch, image_list, label_list, index_dequeue_op, enqueue_op, image_paths_placeholder, labels_placeholder,
learning_rate_placeholder, phase_train_placeholder, batch_size_placeholder, global_step,
total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file)
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, step)
# Evaluate on LFW
if args.lfw_dir:
evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder,
embeddings, label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer)
sess.close()
return model_dir
def main(args):
network = importlib.import_module(args.model_def)
image_size = (args.image_size, args.image_size)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.makedirs(log_dir)
model_dir = os.path.join(os.path.expanduser(args.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.makedirs(model_dir)
stat_file_name = os.path.join(log_dir, 'stat.h5')
# Write arguments to a text file
facenet.write_arguments_to_file(args, os.path.join(log_dir, 'arguments.txt'))
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(sys.argv))
np.random.seed(seed=args.seed)
random.seed(args.seed)
dataset = facenet.get_dataset(args.data_dir)
if args.filter_filename:
dataset = filter_dataset(dataset, os.path.expanduser(args.filter_filename),
args.filter_percentile, args.filter_min_nrof_images_per_class)
if args.validation_set_split_ratio>0.0:
train_set, val_set = facenet.split_dataset(dataset, args.validation_set_split_ratio, args.min_nrof_val_images_per_class, 'SPLIT_IMAGES')
else:
train_set, val_set = dataset, []
nrof_classes = len(train_set)
print('Model directory: %s' % model_dir)
print('Log directory: %s' % log_dir)
pretrained_model = None
if args.pretrained_model:
pretrained_model = os.path.expanduser(args.pretrained_model)
print('Pre-trained model: %s' % pretrained_model)
if args.lfw_dir:
print('LFW directory: %s' % args.lfw_dir)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
# Get the paths for the corresponding images
lfw_paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs)
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
global_step = tf.Variable(0, trainable=False)
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list)>0, 'The training set should not be empty'
val_image_list, val_label_list = facenet.get_image_paths_and_labels(val_set)
# Create a queue that produces indices into the image_list and label_list
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
index_queue = tf.train.range_input_producer(range_size, num_epochs=None,
shuffle=True, seed=None, capacity=32)
index_dequeue_op = index_queue.dequeue_many(args.batch_size*args.epoch_size, 'index_dequeue')
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,1), name='image_paths')
labels_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='labels')
control_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='control')
nrof_preprocess_threads = 4
input_queue = data_flow_ops.FIFOQueue(capacity=2000000,
dtypes=[tf.string, tf.int32, tf.int32],
shapes=[(1,), (1,), (1,)],
shared_name=None, name=None)
enqueue_op = input_queue.enqueue_many([image_paths_placeholder, labels_placeholder, control_placeholder], name='enqueue_op')
image_batch, label_batch = facenet.create_input_pipeline(input_queue, image_size, nrof_preprocess_threads, batch_size_placeholder)
image_batch = tf.identity(image_batch, 'image_batch')
image_batch = tf.identity(image_batch, 'input')
label_batch = tf.identity(label_batch, 'label_batch')
print('Number of classes in training set: %d' % nrof_classes)
print('Number of examples in training set: %d' % len(image_list))
print('Number of classes in validation set: %d' % len(val_set))
print('Number of examples in validation set: %d' % len(val_image_list))
print('Building training graph')
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
logits = slim.fully_connected(prelogits, len(train_set), activation_fn=None,
weights_initializer=slim.initializers.xavier_initializer(),
weights_regularizer=slim.l2_regularizer(args.weight_decay),
scope='Logits', reuse=False)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Norm for the prelogits
eps = 1e-4
prelogits_norm = tf.reduce_mean(tf.norm(tf.abs(prelogits)+eps, ord=args.prelogits_norm_p, axis=1))
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_norm * args.prelogits_norm_loss_factor)
# Add center loss
prelogits_center_loss, _ = facenet.center_loss(prelogits, label_batch, args.center_loss_alfa, nrof_classes)
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_center_loss * args.center_loss_factor)
learning_rate = tf.train.exponential_decay(learning_rate_placeholder, global_step,
args.learning_rate_decay_epochs*args.epoch_size, args.learning_rate_decay_factor, staircase=True)
tf.summary.scalar('learning_rate', learning_rate)
# Calculate the average cross entropy loss across the batch
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch, logits=logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
correct_prediction = tf.cast(tf.equal(tf.argmax(logits, 1), tf.cast(label_batch, tf.int64)), tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
# Calculate the total losses
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([cross_entropy_mean] + regularization_losses, name='total_loss')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay, tf.global_variables(), args.log_histograms)
# Create a saver
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
summary_writer = tf.summary.FileWriter(log_dir, sess.graph)
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
with sess.as_default():
if pretrained_model:
print('Restoring pretrained model: %s' % pretrained_model)
saver.restore(sess, pretrained_model)
# Training and validation loop
print('Running training')
nrof_steps = args.max_nrof_epochs*args.epoch_size
nrof_val_samples = int(math.ceil(args.max_nrof_epochs / args.validate_every_n_epochs)) # Validate every validate_every_n_epochs as well as in the last epoch
stat = {
'loss': np.zeros((nrof_steps,), np.float32),
'center_loss': np.zeros((nrof_steps,), np.float32),
'reg_loss': np.zeros((nrof_steps,), np.float32),
'xent_loss': np.zeros((nrof_steps,), np.float32),
'prelogits_norm': np.zeros((nrof_steps,), np.float32),
'accuracy': np.zeros((nrof_steps,), np.float32),
'val_loss': np.zeros((nrof_val_samples,), np.float32),
'val_xent_loss': np.zeros((nrof_val_samples,), np.float32),
'val_accuracy': np.zeros((nrof_val_samples,), np.float32),
'lfw_accuracy': np.zeros((args.max_nrof_epochs,), np.float32),
'lfw_valrate': np.zeros((args.max_nrof_epochs,), np.float32),
'learning_rate': np.zeros((args.max_nrof_epochs,), np.float32),
'time_train': np.zeros((args.max_nrof_epochs,), np.float32),
'time_validate': np.zeros((args.max_nrof_epochs,), np.float32),
'time_evaluate': np.zeros((args.max_nrof_epochs,), np.float32),
'prelogits_hist': np.zeros((args.max_nrof_epochs, 1000), np.float32),
}
for epoch in range(1,args.max_nrof_epochs+1):
step = sess.run(global_step, feed_dict=None)
# Train for one epoch
t = time.time()
cont = train(args, sess, epoch, image_list, label_list, index_dequeue_op, enqueue_op, image_paths_placeholder, labels_placeholder,
learning_rate_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder, global_step,
total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file,
stat, cross_entropy_mean, accuracy, learning_rate,
prelogits, prelogits_center_loss, args.random_rotate, args.random_crop, args.random_flip, prelogits_norm, args.prelogits_hist_max, args.use_fixed_image_standardization)
stat['time_train'][epoch-1] = time.time() - t
if not cont:
break
t = time.time()
if len(val_image_list)>0 and ((epoch-1) % args.validate_every_n_epochs == args.validate_every_n_epochs-1 or epoch==args.max_nrof_epochs):
validate(args, sess, epoch, val_image_list, val_label_list, enqueue_op, image_paths_placeholder, labels_placeholder, control_placeholder,
phase_train_placeholder, batch_size_placeholder,
stat, total_loss, regularization_losses, cross_entropy_mean, accuracy, args.validate_every_n_epochs, args.use_fixed_image_standardization)
stat['time_validate'][epoch-1] = time.time() - t
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, subdir, epoch)
# Evaluate on LFW
t = time.time()
if args.lfw_dir:
evaluate(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
embeddings, label_batch, lfw_paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, log_dir, step, summary_writer, stat, epoch,
args.lfw_distance_metric, args.lfw_subtract_mean, args.lfw_use_flipped_images, args.use_fixed_image_standardization)
stat['time_evaluate'][epoch-1] = time.time() - t
print('Saving statistics')
with h5py.File(stat_file_name, 'w') as f:
for key, value in stat.iteritems():
f.create_dataset(key, data=value)
return model_dir
def train():
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, test_set = facenet.split_dataset(dataset, 0.9)
fileName = "/home/david/debug4.h5"
f = h5py.File(fileName, "r")
for item in f.values():
print(item)
w1 = f['1w'][:]
b1 = f['1b'][:]
f.close()
print(w1.shape)
print(b1.shape)
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, 96, 96, 3), name='Input')
# Build a Graph that computes the logits predictions from the inference model
#embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, phase_train=True)
conv1 = _conv(images_placeholder, 3, 64, 7, 7, 2, 2, 'SAME', 'conv1_7x7', phase_train=False, use_batch_norm=False, init_weight=w1, init_bias=b1)
resh1 = tf.reshape(conv1, [-1, 294912])
embeddings = _affine(resh1, 294912, 128)
# Split example embeddings into anchor, positive and negative
a, p, n = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(a, p, n)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, grads = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def)
epoch = 0
with sess.as_default():
while epoch<FLAGS.max_nrof_epochs:
batch_number = 0
while batch_number<FLAGS.epoch_size:
print('Loading new data')
image_data, num_per_class, image_paths = facenet.load_data(train_set)
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = FLAGS.people_per_batch*FLAGS.images_per_person
nrof_batches_per_epoch = int(np.floor(nrof_examples_per_epoch/FLAGS.batch_size))
if True:
for i in xrange(nrof_batches_per_epoch):
feed_dict, _ = facenet.get_batch(images_placeholder, image_data, i)
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Select triplets based on the embeddings
apn, nrof_random_negs, nrof_triplets = facenet.select_triplets(emb_array, num_per_class, image_data)
duration = time.time() - start_time
print('(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' % (nrof_random_negs, nrof_triplets, duration))
count = 0
while count<nrof_triplets*3 and batch_number<FLAGS.epoch_size:
start_time = time.time()
feed_dict, batch = facenet.get_batch(images_placeholder, apn, batch_number)
if (batch_number%20==0):
err, summary_str, _ = sess.run([loss, summary_op, train_op], feed_dict=feed_dict)
summary_writer.add_summary(summary_str, FLAGS.epoch_size*epoch+batch_number)
else:
err, _ = sess.run([loss, train_op], feed_dict=feed_dict)
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f' % (epoch, batch_number, FLAGS.epoch_size, duration, err))
batch_number+=1
count+=FLAGS.batch_size
else:
while batch_number<FLAGS.epoch_size:
start_time = time.time()
feed_dict, _ = facenet.get_batch(images_placeholder, image_data, batch_number)
grad_tensors, grad_vars = zip(*grads)
eval_list = (train_op, loss) + grad_tensors
result = sess.run(eval_list, feed_dict=feed_dict)
grads_eval = result[2:]
nrof_parameters = 0
for gt, gv in zip(grads_eval, grad_vars):
print('%40s: %6d' % (gv.op.name, np.size(gt)))
nrof_parameters += np.size(gt)
print('Total number of parameters: %d' % nrof_parameters)
err = result[1]
batch_number+=1
epoch+=1
# Save the model checkpoint periodically.
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=epoch*FLAGS.epoch_size+batch_number)
def main(args):
np.random.seed(seed=args.seed)
random.seed(args.seed)
train_set = facenet.get_dataset(args.data_dir)
result_filename = os.path.join(os.path.expanduser(args.data_dir),
'statistics.txt')
with tf.Graph().as_default():
tf.set_random_seed(args.seed)
# Get a list of image paths and their labels
image_list, _ = facenet.get_image_paths_and_labels(train_set)
nrof_images = len(image_list)
assert nrof_images > 0, 'The dataset should not be empty'
input_queue = tf.train.string_input_producer(image_list,
num_epochs=None,
shuffle=False,
seed=None,
capacity=32)
nrof_preprocess_threads = 4
images = []
for _ in range(nrof_preprocess_threads):
filename = input_queue.dequeue()
file_contents = tf.read_file(filename)
image = tf.image.decode_image(file_contents)
image = tf.image.resize_image_with_crop_or_pad(image, 160, 160)
#pylint: disable=no-member
image.set_shape((args.image_size, args.image_size, 3))
image = tf.cast(image, tf.float32)
images.append((image, ))
image_batch = tf.train.batch_join(images,
batch_size=100,
allow_smaller_final_batch=True)
#mean = tf.reduce_mean(image_batch, reduction_indices=[0,1,2])
m, v = tf.nn.moments(image_batch, [1, 2])
mean = tf.reduce_mean(m, 0)
variance = tf.reduce_mean(v, 0)
# Start running operations on the Graph.
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=args.gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)
with sess.as_default():
# Training and validation loop
print('Running training')
nrof_batches = nrof_images // args.batch_size
#nrof_batches = 20
means = np.zeros(shape=(nrof_batches, 3), dtype=np.float32)
variances = np.zeros(shape=(nrof_batches, 3), dtype=np.float32)
for i in range(nrof_batches):
means[i, :], variances[i, :] = sess.run([mean, variance])
if (i + 1) % 10 == 0:
print('Batch: %5d/%5d, Mean: %s, Variance: %s' %
(i + 1, nrof_batches,
np.array_str(np.mean(means[:i, :], axis=0)),
np.array_str(np.mean(variances[:i, :], axis=0))))
dataset_mean = np.mean(means, axis=0)
dataset_variance = np.mean(variances, axis=0)
print('Final mean: %s' % np.array_str(dataset_mean))
print('Final variance: %s' % np.array_str(dataset_variance))
with open(result_filename, 'w') as text_file:
print('Writing result to %s' % result_filename)
text_file.write(
'Mean: %.5f, %.5f, %.5f\n' %
(dataset_mean[0], dataset_mean[1], dataset_mean[2]))
text_file.write('Variance: %.5f, %.5f, %.5f\n' %
(dataset_variance[0], dataset_variance[1],
dataset_variance[2]))
