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, 'inference')
train_set = 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(train_set)
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)
prelogits, _ = network.inference(image_batch, 1.0,
phase_train=False, weight_decay=0.0, reuse=False)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
saver.restore(sess, os.path.join(os.path.expanduser(args.model_file)))
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(train_set)
label_array = np.array(label_list)
class_names = [cls.name for cls in train_set]
nrof_examples_per_class = [ len(cls.image_paths) for cls in train_set ]
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, '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, '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
