def main(args):
with tf.Graph().as_default():
images_placeholder = tf.placeholder(tf.float32, shape=(None,args.image_size,args.image_size,3), name='input')
with tf.Session() as sess:
print('Loading graphdef: %s' % args.model_file)
with gfile.FastGFile(os.path.expanduser(args.model_file),'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
return_elements = ['phase_train:0', 'embeddings:0']
phase_train_placeholder, embeddings = tf.import_graph_def(graph_def, input_map={'input':images_placeholder},
return_elements=return_elements, name='import')
# 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)
# Evaluate
tpr, fpr, accuracy, val, val_std, far = lfw.validate(sess, 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))
facenet.plot_roc(fpr, tpr, 'NN4')
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# 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)
# Load the model
print('Loading model "%s"' % args.model_file)
facenet.load_model(args.model_file)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
tpr, fpr, accuracy, val, val_std, far = lfw.validate(sess,
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))
facenet.plot_roc(fpr, tpr, 'NN4')
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# 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)
# Load the model
print('Model directory: %s' % args.model_dir)
meta_file, ckpt_file = facenet.get_model_filenames(os.path.expanduser(args.model_dir))
print('Metagraph file: %s' % meta_file)
print('Checkpoint file: %s' % ckpt_file)
facenet.load_model(args.model_dir, meta_file, ckpt_file)
# 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")
image_size = images_placeholder.get_shape()[1]
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
batch_size = args.lfw_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches):
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)
tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(emb_array,
actual_issame, 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))
auc = metrics.auc(fpr, tpr)
print('Area Under Curve (AUC): %1.3f' % auc)
eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x), 0., 1.)
print('Equal Error Rate (EER): %1.3f' % eer)
def main(args):
pairs_file = r"./pairs.txt"
lfw_dir = r"./lfw-deepfunneled"
# pairs_file = r"C:\sources\PycharmProjects\facenet\data\pairs.txt"
# lfw_dir = r"D:\datasets\lfw\lfw-deepfunneled"
pairs = lfw.read_pairs(pairs_file)
lfw_paths, same_list = lfw.get_paths(lfw_dir, pairs, "jpg")
embedding_list, real_same_list = dlib_generate_embedding(lfw_paths, same_list)
tpr, fpr, accuracy = evaluate(embedding_list, real_same_list)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
auc = metrics.auc(fpr, tpr)
print('Area Under Curve (AUC): %1.3f' % auc)
def evaluate_double(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder,
embeddings, labels, image_paths, actual_issame, batch_size, nrof_folds, log_dir, step, summary_writer,best_accuracy,saver_save,model_dir,subdir,images_placeholder,args):
start_time = time.time()
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
batch_size = args.lfw_batch_size
nrof_images = len(paths) #图片的数量
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size))
#math.ceil为向上取整，意味这最后一个batch可能样本数少于batch_size
emb_array = np.zeros((nrof_images, args.embedding_size))
for i in range(nrof_batches):
start_index = i*batch_size
end_index = min((i+1)*batch_size, nrof_images)#保证最后一个batch的正确性
paths_batch = paths[start_index:end_index]
images = load_data(paths_batch)
#by charles
images_flip = np.flip(images, 2)
feed_dict = { images_placeholder:images, phase_train_placeholder:False }
feed_dict_flip = { images_placeholder:images_flip, phase_train_placeholder:False }
emb = sess.run(embeddings, feed_dict=feed_dict)
emb_flip = sess.run(embeddings, feed_dict=feed_dict_flip)
emb_average = (emb + emb_flip)/2.0
emb_array[start_index:end_index,:] = emb_average
accuracy,thre = evaluate_with_no_cv(emb_array, actual_issame)
if np.mean(accuracy) > best_accuracy:
save_variables_and_metagraph(sess, saver_save, summary_writer, model_dir, subdir, step)
best_accuracy = np.mean(accuracy)
print('Accuracy: %1.3f Threshold: %1.3f' % (accuracy,thre))
lfw_time = time.time() - start_time
# Add validation loss and accuracy to summary
summary = tf.Summary()
#pylint: disable=maybe-no-member
summary.value.add(tag='lfw/accuracy', simple_value=accuracy)
summary.value.add(tag='time/lfw', simple_value=lfw_time)
summary_writer.add_summary(summary, step)
return best_accuracy
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# 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)
image_paths_placeholder = tf.placeholder(tf.string, shape=(None,1), name='image_paths')
labels_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='labels')
batch_size_placeholder = tf.placeholder(tf.int32, name='batch_size')
control_placeholder = tf.placeholder(tf.int32, shape=(None,1), name='control')
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
nrof_preprocess_threads = 4
image_size = (args.image_size, args.image_size)
eval_input_queue = data_flow_ops.FIFOQueue(capacity=2000000,
dtypes=[tf.string, tf.int32, tf.int32],
shapes=[(1,), (1,), (1,)],
shared_name=None, name=None)
eval_enqueue_op = eval_input_queue.enqueue_many([image_paths_placeholder, labels_placeholder, control_placeholder], name='eval_enqueue_op')
image_batch, label_batch = facenet.create_input_pipeline(eval_input_queue, image_size, nrof_preprocess_threads, batch_size_placeholder)
# Load the model
input_map = {'image_batch': image_batch, 'label_batch': label_batch, 'phase_train': phase_train_placeholder}
facenet.load_model(args.model, input_map=input_map)
# Get output tensor
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
#
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
evaluate(sess, eval_enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholder, control_placeholder,
embeddings, label_batch, paths, actual_issame, args.lfw_batch_size, args.lfw_nrof_folds, args.distance_metric, args.subtract_mean,
args.use_flipped_images, args.use_fixed_image_standardization)
def load_testset(size):
# Load images paths and labels
pairs = lfw.read_pairs(pairs_path)
paths, labels = lfw.get_paths(testset_path, pairs, file_extension)
# Random choice
permutation = np.random.choice(len(labels), size, replace=False)
paths_batch_1 = []
paths_batch_2 = []
for index in permutation:
paths_batch_1.append(paths[index * 2])
paths_batch_2.append(paths[index * 2 + 1])
labels = np.asarray(labels)[permutation]
paths_batch_1 = np.asarray(paths_batch_1)
paths_batch_2 = np.asarray(paths_batch_2)
# Load images
faces1 = facenet.load_data(paths_batch_1, False, False, image_size)
faces2 = facenet.load_data(paths_batch_2, False, False, image_size)
# Change pixel values to 0 to 1 values
min_pixel = min(np.min(faces1), np.min(faces2))
max_pixel = max(np.max(faces1), np.max(faces2))
faces1 = (faces1 - min_pixel) / (max_pixel - min_pixel)
faces2 = (faces2 - min_pixel) / (max_pixel - min_pixel)
# Convert labels to one-hot vectors
onehot_labels = []
for index in range(len(labels)):
if labels[index]:
onehot_labels.append([1, 0])
else:
onehot_labels.append([0, 1])
return faces1, faces2, np.array(onehot_labels)
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) #类目数
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为两两比较的列表,列表的元素为有2个元素的元祖,actual_issame为列表,表示每个元素是否为同一个人
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) #capacity代表队列容量
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(),
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_out = tf.train.Saver(tf.trainable_variables(), max_to_keep=3) #max_to_keep代表保存最近的3个模型;如果设置为0或None,则代表保存每一个模型,会占用很大内存(不推荐)
# 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) #设置GPU显存占用率
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)
# tensorflow中的多进程管理,下面两条语句通常配套使用
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)
facenet.load_model(pretrained_model)
# Training and validation loop
print('Running softmax 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_out, 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.items():
f.create_dataset(key, data=value)
return model_dir
from __future__ import division
import numpy as np
import os
import sys
sys.path.append(os.path.join(os.path.dirname(__file__), 'eval'))
import lfw
import sklearn
from sklearn.decomposition import PCA
lfw_dir = '/raid5data/dplearn/lfw_mtcnn2'
lfw_pairs = lfw.read_pairs(os.path.join(lfw_dir, 'pairs.txt'))
lfw_paths, issame_list = lfw.get_paths(lfw_dir, lfw_pairs, 'jpg')
model_dir = '../model'
models = ['sphereface_p0_20-lfw-0006.npy']
models = ['sphereface-64-p0_0_96_95_0-lfw-0001.npy']
models = ['sphereface_p0_20-lfw-0006.npy', 'sphereface-64-p0_0_96_95_0-lfw-0001.npy']
models = ['sphereface-20-p0_0_96_112_0-lfw-0022.npy','sphereface-20-p0_0_96_95_0-lfw-0021.npy', 'sphereface-20-p0_40_96_112_0-lfw-0022.npy']
models = ['sphereface-20-p0_0_96_112_0-lfw-0022.npy','sphereface-20-p0_0_96_95_0-lfw-0021.npy', 'sphereface-36-p0_0_96_112_0-lfw-0022.npy']
models = ['sphereface-20-p0_0_96_112_0-lfw-0022.npy','sphereface-20-p0_0_96_95_0-lfw-0021.npy']
models = ['sphereface-20-p0_0_96_112_0-lfw-0022.npy','sphereface-20-p0_0_96_95_0-lfw-0021.npy', 'sphereface-36-p0_0_96_112_0-lfw-0022.npy']
models = ['sphereface-20-p0_0_96_112_0-lfw-0022.npy','sphereface-20-p0_0_96_95_0-lfw-0021.npy', 'sphereface-36-p0_0_96_95_0-lfw-0021.npy']
models = [
#'sphereface-20-p0_0_96_112_0-lfw-0022.npy',
#'sphereface-20-p0_0_96_95_0-lfw-0021.npy',
#'sphereface-20-p0_0_80_95_0-lfw-0021.npy',
#'sphereface-36-p0_0_96_95_0-lfw-0021.npy',
'sphereface-s60-p0_0_96_112_0-lfw-0031.npy',
'sphereface-s60-p0_0_96_95_0-lfw-0021.npy',
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.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
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
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(
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.global_variables(), args.log_histograms)
# Evaluation
if args.lfw_dir:
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,
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.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,
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)
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)
# 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():
model = "20190128-123456/3001w-train.pb"
pairs = lfw.read_pairs('../database/npairs.txt')
paths, actual_issame = lfw.get_paths('F:/aface-clean-rename2', pairs)
true_pairs = []
false_pairs = []
with tf.Graph().as_default():
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))
with sess.as_default():
# Load the model
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")
for i in range(len(pairs)):
print(paths[2 * i])
img1 = cv2.imread(paths[2 * i])
img2 = cv2.imread(paths[2 * i + 1])
frame1 = cv2.cvtColor(img1, cv2.COLOR_BGR2RGB)
frame2 = cv2.cvtColor(img2, cv2.COLOR_BGR2RGB)
f1 = []
f2 = []
prewhitened1 = facenet.prewhiten(frame1)
f1.append(prewhitened1)
prewhitened2 = facenet.prewhiten(frame2)
f2.append(prewhitened2)
feed_dict = {
images_placeholder: f1,
phase_train_placeholder: False
}
emb1 = sess.run(embeddings, feed_dict=feed_dict)
feed_dict = {
images_placeholder: f2,
phase_train_placeholder: False
}
emb2 = sess.run(embeddings, feed_dict=feed_dict)
sim = dot(emb1, emb2.T)
sim = sim * 0.5 + 0.5
if actual_issame[i] == True:
true_pairs.append(sim)
else:
false_pairs.append(sim)
thresholds = np.arange(0, 1, 0.01)
total_ratelist = []
total_rightnum = 0
total_rightnum2 = 0
f = open('../database/restlt.txt', 'w')
f.truncate()
for threshold in thresholds:
# print(threshold)
true_num = 0
false_num = 0
for i in range(len(true_pairs)):
if float(true_pairs[i]) > threshold:
true_num = true_num + 1
for j in range(len(false_pairs)):
if float(false_pairs[j]) < threshold:
false_num = false_num + 1
if (true_num + false_num) >= total_rightnum2:
total_rightnum2 = true_num + false_num
print(total_rightnum2)
print(threshold, ':',
format(float(total_rightnum2) / float(len(pairs)), '.4f'))
total_rightnum = true_num + false_num
f.writelines([
str(threshold), ' ',
str(format(float(total_rightnum) / float(len(pairs)), '.4f')), '\n'
])
f.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)
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(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# 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)
image_paths_placeholder = tf.placeholder(tf.string,
shape=(None, 1),
name='image_paths')
labels_placeholder = tf.placeholder(tf.int32,
shape=(None, 1),
name='labels')
batch_size_placeholder = tf.placeholder(tf.int32,
name='batch_size')
control_placeholder = tf.placeholder(tf.int32,
shape=(None, 1),
name='control')
phase_train_placeholder = tf.placeholder(tf.bool,
name='phase_train')
nrof_preprocess_threads = 4
image_size = (args.image_size, args.image_size)
eval_input_queue = data_flow_ops.FIFOQueue(
capacity=2000000,
dtypes=[tf.string, tf.int32, tf.int32],
shapes=[(1, ), (1, ), (1, )],
shared_name=None,
name=None)
eval_enqueue_op = eval_input_queue.enqueue_many(
[
image_paths_placeholder, labels_placeholder,
control_placeholder
],
name='eval_enqueue_op')
image_batch, label_batch = facenet.create_input_pipeline(
eval_input_queue, image_size, nrof_preprocess_threads,
batch_size_placeholder)
# Load the model
input_map = {
'image_batch': image_batch,
'label_batch': label_batch,
'phase_train': phase_train_placeholder
}
facenet.load_model(args.model, input_map=input_map)
# Get output tensor
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
#
coord = tf.train.Coordinator()
tf.train.start_queue_runners(coord=coord, sess=sess)
evaluate(sess, eval_enqueue_op, image_paths_placeholder,
labels_placeholder, phase_train_placeholder,
batch_size_placeholder, control_placeholder, embeddings,
label_batch, paths, actual_issame, args.lfw_batch_size,
args.lfw_nrof_folds, args.distance_metric,
args.subtract_mean, args.use_flipped_images,
args.use_fixed_image_standardization)
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(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# 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)
# Load the model
print('Model directory: %s' % args.model_dir)
meta_file, ckpt_file = facenet.get_model_filenames(
os.path.expanduser(args.model_dir))
print('Metagraph file: %s' % meta_file)
print('Checkpoint file: %s' % ckpt_file)
facenet.load_model(args.model_dir, meta_file, ckpt_file)
# 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")
image_size = images_placeholder.get_shape()[1]
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
batch_size = args.lfw_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0 * nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches):
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)
tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(
emb_array, actual_issame, 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))
facenet.plot_roc(fpr, tpr, 'NN4')
import os
sys.path.append("/data/yy/github/insightface/src/eval")
sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'eval'))
import lfw
import cv2
parser = argparse.ArgumentParser(description='Package LFW images')
# general
parser.add_argument('--data-dir', default='./', help='')
parser.add_argument('--image-size', type=str, default='112,112', help='')
parser.add_argument('--racial-dir', type=str, default='', help='')
parser.add_argument('--output', default='val.bin', help='path to save.')
parser.add_argument('--photo-dir', default='', help='path to save.')
args = parser.parse_args()
lfw_dir = args.data_dir
image_size = [int(x) for x in args.image_size.split(',')]
lfw_pairs = lfw.read_pairs(args.data_dir) #os.path.join(lfw_dir, 'pairs.txt'))
print("lfw_dir, lfw_pairs", lfw_dir, lfw_pairs)
lfw_paths, issame_list = lfw.get_paths(args.photo_dir, lfw_pairs, 'jpg')
lfw_bins = []
print(len(issame_list))
#lfw_data = nd.empty((len(lfw_paths), 3, image_size[0], image_size[1]))
i = 0
for path in lfw_paths:
with open(path, 'rb') as fin:
#img = mx.image.imdecode(fin.read())
#img = mx.image.imresize(img, 112, 112)
img = cv2.imread(path)
img = cv2.resize(img, (112, 112))
ret, buf = cv2.imencode(".jpg", img)
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.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_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')
# 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)
trainable_variables = tf.trainable_variables()
variable_to_finetuning = [
v for v in trainable_variables if not v.name.startswith('Logits')
]
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.trainable_variables(), args.log_histograms)
# Create a saver
saver = tf.train.Saver(variable_to_finetuning, 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:
# 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)
# Load the model
facenet.load_model(args.model)
# TODO: replace near 0 parameters to 0
# trainable_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES)
# print("trainable_vars", len(trainable_vars))
# zero_threshold = 1e-2
# n_var_elements = 0
# n_non_zero = 0
# n_non_zero_after = 0
# assign_ops = []
# for var in trainable_vars:
# matrix = var.eval(sess)
# # if var.name.endswith("weights:0"):
# # print(matrix)
# n_var_elements += np.size(matrix)
# n_non_zero += np.count_nonzero(matrix)
# # matrix[np.abs(matrix)<=zero_threshold] = 0
# # n_non_zero_after += np.count_nonzero(matrix)
# # assign_ops.append(var.assign(matrix))
#
# print("non_zero: ",n_non_zero,n_var_elements,n_non_zero/n_var_elements)
# print("non_zero after: ",n_non_zero_after,n_var_components,n_non_zero_after/n_var_components)
# sess.run(assign_ops)
# Get input and output tensors
graph = tf.get_default_graph()
images_placeholder = graph.get_tensor_by_name("input:0")
embeddings = graph.get_tensor_by_name("embeddings:0")
phase_train_placeholder = graph.get_tensor_by_name("phase_train:0")
#image_size = images_placeholder.get_shape()[1] # For some reason this doesn't work for frozen graphs
image_size = args.image_size
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
start_time = time.time()
batch_size = args.lfw_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0 * nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches):
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)
duration = time.time() - start_time
print('Forward pass duration in %.3f seconds' % duration)
tpr, fpr, recall, precision, accuracy, val, val_std, far = lfw.evaluate(
emb_array, actual_issame, nrof_folds=args.lfw_nrof_folds)
print('Accuracy: %1.3f+-%1.3f' %
(np.mean(accuracy), np.std(accuracy)))
print('Precision: %1.3f+-%1.3f' %
(np.mean(precision), np.std(precision)))
print('Recall: %1.3f+-%1.3f' % (np.mean(recall), np.std(recall)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' %
(val, val_std, far))
auc = metrics.auc(fpr, tpr)
print('Area Under Curve (AUC): %1.3f' % auc)
eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x),
0., 1.)
print('Equal Error Rate (EER): %1.3f' % eer)
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')
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
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())
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)
return model_dir
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Read the file containing the pairs used for testing
# 读取包含用于 test 的 pairs 的文件
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
#pdb.set_trace()
# Get the paths for the corresponding images
# 获取相应图像的路径
print('###' * 10, args.lfw_dir)
paths, actual_issame = lfw.get_paths(
os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
# image_size = images_placeholder.get_shape()[1] # For some reason this doesn't work for frozen graphs
# 图像的 size
image_size = args.image_size
print('image size', image_size)
# images_placeholder = tf.placeholder(tf.float32,shape=(None,image_size,image_size,3),name='image')
# 图像的占位符
images_placeholder = tf.placeholder(tf.float32,
shape=(None, args.image_height,
args.image_width, 3),
name='image')
# 阶段占位符
phase_train_placeholder = tf.placeholder(tf.bool,
name='phase_train')
#with slim.arg_scope(resnet_v1.resnet_arg_scope(False)):
# 判断 网络结构，以便更好测试
if args.network_type == 'resnet50':
with slim.arg_scope(resnet_v2.resnet_arg_scope(False)):
# 获取 resnet50 的 prelogits 和 end_points
prelogits, end_points = resnet_v2.resnet_v2_50(
images_placeholder,
is_training=phase_train_placeholder,
num_classes=256,
output_stride=16)
#prelogits, end_points = resnet_v2.resnet_v2_50(images_placeholder,is_training=phase_train_placeholder,num_classes=256,output_stride=8)
#prelogits, end_points = resnet_v2_modify.resnet_v2_50(images_placeholder,is_training=phase_train_placeholder,num_classes=256)
#prelogits = slim.batch_norm(prelogits, is_training=phase_train_placeholder,epsilon=1e-5, scale=True,scope='softmax_bn')
prelogits = tf.squeeze(prelogits, [1, 2],
name='SpatialSqueeze')
# 网络结构如果是 sphere_network
elif args.network_type == 'sphere_network':
# 获取 sphere 网络的 prelogits，即运行网络的 inference
prelogits = network.infer(images_placeholder,
args.embedding_size)
# 判断是否进行 batch norm
if args.fc_bn:
print('do batch norm after network')
# 进行 batch norm
prelogits = slim.batch_norm(
prelogits,
is_training=phase_train_placeholder,
epsilon=1e-5,
scale=True,
scope='softmax_bn')
elif args.network_type == 'inception_resnet_v1':
prelogits, _ = network_2.inference(images_placeholder, 1, True,
args.embedding_size, 0.0,
False)
# embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# 返回与输入相同的形状和内容的 tensor
embeddings = tf.identity(prelogits)
#saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
saver = tf.train.Saver(tf.global_variables(), max_to_keep=3)
saver.restore(sess, args.model)
if args.save_model:
saver.save(sess, './tmp_saved_model', global_step=1)
return 0
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
batch_size = args.lfw_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0 * nrof_images / batch_size))
if args.do_flip:
embedding_size *= 2
emb_array = np.zeros((nrof_images, embedding_size))
else:
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches):
start_index = i * batch_size
print('handing {}/{}'.format(start_index, nrof_images))
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,True,image_size)
#images = facenet.load_data2(paths_batch, False, False, args.image_height,args.image_width,True,)
images = utils.load_data(paths_batch, False, False,
args.image_height, args.image_width,
args.prewhiten,
(args.image_height, args.image_width))
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
feats = sess.run(embeddings, feed_dict=feed_dict)
if args.do_flip:
images_flip = utils.load_data(
paths_batch, False, True, args.image_height,
args.image_width, args.prewhiten,
(args.image_height, args.image_width))
feed_dict = {
images_placeholder: images_flip,
phase_train_placeholder: False
}
feats_flip = sess.run(embeddings, feed_dict=feed_dict)
feats = np.concatenate((feats, feats_flip), axis=1)
#feats = (feats+feats_flip)/2
#images = facenet.load_data(paths_batch, False, False, 160,True,182)
#images = facenet.load_data(paths_batch, False, False, image_size,src_size=256)
#feed_dict = { images_placeholder:images, phase_train_placeholder:True}
#pdb.set_trace()
#feats = facenet.prewhiten(feats)
feats = utils.l2_normalize(feats)
# print('sssssssssss', feats)
emb_array[start_index:end_index, :] = feats
# print('aaaaaaaaaa', emb_array)
#pdb.set_trace()
tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(
emb_array, actual_issame, 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))
auc = metrics.auc(fpr, tpr)
print('Area Under Curve (AUC): %1.3f' % auc)
eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x),
0., 1.)
print('Equal Error Rate (EER): %1.3f' % eer)
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# 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)
# Load the model
print('Model directory: %s' % args.model_dir)
meta_file, ckpt_file = facenet.get_model_filenames(os.path.expanduser(args.model_dir))
print('Metagraph file: %s' % meta_file)
print('Checkpoint file: %s' % ckpt_file)
facenet.load_model(args.model_dir, meta_file, ckpt_file)
# 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")
image_size = images_placeholder.get_shape()[1]
embedding_size = embeddings.get_shape()[1]
image_size = image_size.value
# pdb.set_trace()
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
batch_size = args.lfw_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
print('nrof_batches :{}'.format(nrof_batches))
all_time = 0
for i in range(nrof_batches):
start_index = i*batch_size
end_index = min((i+1)*batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
# pdb.set_trace()
images = facenet.load_data(paths_batch, False, False, image_size)
feed_dict = {images_placeholder:images}
start = time()
emb_array[start_index:end_index,:] = sess.run(embeddings, feed_dict=feed_dict)
end = time()
all_time += (end - start)
print('index: {} time: {}'.format(i, (end-start)))
# pdb.set_trace()
print('all_time :', all_time)
msgpack_numpy.dump((paths, emb_array, actual_issame), open('lfw_feature.p', 'wb'))
tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(emb_array,
args.seed, actual_issame, nrof_folds=args.lfw_nrof_folds)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(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.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):
pairs = lfw.read_pairs(os.path.expanduser(args.lfw_pairs))
paths, actual_issame = lfw.get_paths(os.path.expanduser(args.lfw_dir), pairs, args.lfw_file_ext)
result_dir = '../data/'
plt.ioff() # Disable interactive plotting mode
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
print('Loading model "%s"' % args.model_file)
facenet.load_model(args.model_file)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
image_size = int(images_placeholder.get_shape()[1])
# Run test on LFW to check accuracy for different horizontal/vertical translations of input images
if args.nrof_offsets>0:
step = 3
offsets = np.asarray([x*step for x in range(-args.nrof_offsets//2+1, args.nrof_offsets//2+1)])
horizontal_offset_accuracy = [None] * len(offsets)
for idx, offset in enumerate(offsets):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, translate_images, (offset,0), 60, args.orig_image_size, args.seed)
print('Hoffset: %1.3f Accuracy: %1.3f+-%1.3f' % (offset, np.mean(accuracy), np.std(accuracy)))
horizontal_offset_accuracy[idx] = np.mean(accuracy)
vertical_offset_accuracy = [None] * len(offsets)
for idx, offset in enumerate(offsets):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, translate_images, (0,offset), 60, args.orig_image_size, args.seed)
print('Voffset: %1.3f Accuracy: %1.3f+-%1.3f' % (offset, np.mean(accuracy), np.std(accuracy)))
vertical_offset_accuracy[idx] = np.mean(accuracy)
fig = plt.figure(1)
plt.plot(offsets, horizontal_offset_accuracy, label='Horizontal')
plt.plot(offsets, vertical_offset_accuracy, label='Vertical')
plt.legend()
plt.grid(True)
plt.title('Translation invariance on LFW')
plt.xlabel('Offset [pixels]')
plt.ylabel('Accuracy')
# plt.show()
print('Saving results in %s' % result_dir)
fig.savefig(os.path.join(result_dir, 'invariance_translation.png'))
save_result(offsets, horizontal_offset_accuracy, os.path.join(result_dir, 'invariance_translation_horizontal.txt'))
save_result(offsets, vertical_offset_accuracy, os.path.join(result_dir, 'invariance_translation_vertical.txt'))
# Run test on LFW to check accuracy for different rotation of input images
if args.nrof_angles>0:
step = 3
angles = np.asarray([x*step for x in range(-args.nrof_offsets//2+1, args.nrof_offsets//2+1)])
rotation_accuracy = [None] * len(angles)
for idx, angle in enumerate(angles):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, rotate_images, angle, 60, args.orig_image_size, args.seed)
print('Angle: %1.3f Accuracy: %1.3f+-%1.3f' % (angle, np.mean(accuracy), np.std(accuracy)))
rotation_accuracy[idx] = np.mean(accuracy)
fig = plt.figure(2)
plt.plot(angles, rotation_accuracy)
plt.grid(True)
plt.title('Rotation invariance on LFW')
plt.xlabel('Angle [deg]')
plt.ylabel('Accuracy')
# plt.show()
print('Saving results in %s' % result_dir)
fig.savefig(os.path.join(result_dir, 'invariance_rotation.png'))
save_result(angles, rotation_accuracy, os.path.join(result_dir, 'invariance_rotation.txt'))
# Run test on LFW to check accuracy for different scaling of input images
if args.nrof_scales>0:
step = 0.05
scales = np.asarray([x*step+1 for x in range(-args.nrof_offsets//2+1, args.nrof_offsets//2+1)])
scale_accuracy = [None] * len(scales)
for scale_idx, scale in enumerate(scales):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, scale_images, scale, 60, args.orig_image_size, args.seed)
print('Scale: %1.3f Accuracy: %1.3f+-%1.3f' % (scale, np.mean(accuracy), np.std(accuracy)))
scale_accuracy[scale_idx] = np.mean(accuracy)
fig = plt.figure(3)
plt.plot(scales, scale_accuracy)
plt.grid(True)
plt.title('Scale invariance on LFW')
plt.xlabel('Scale')
plt.ylabel('Accuracy')
# plt.show()
print('Saving results in %s' % result_dir)
fig.savefig(os.path.join(result_dir, 'invariance_scale.png'))
save_result(scales, scale_accuracy, os.path.join(result_dir, 'invariance_scale.txt'))
def main(args):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory_fraction)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) as sess:
# Read the file containing the pairs used for testing
if args.lfw_pairs == None:
paths, actual_issame = crossFire(getImages(os.path.expanduser(args.lfw_dir)))
print("Crossfire check:", len(actual_issame), "pairs to be checked.")
else:
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)
print("Pair file check:", len(actual_issame), "pairs to be checked.")
# Load the 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")
#image_size = images_placeholder.get_shape()[1] # For some reason this doesn't work for frozen graphs
image_size = args.image_size
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
batch_size = args.lfw_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches):
print('Compute batch:', i, '/', nrof_batches, end='\r')
start_index = i*batch_size
end_index = min((i+1)*batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data2(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)
print()
print('--- Evaluate ---')
tpr, fpr, accuracy, bestThreshold, minThreshold, maxThreshold, val, val_std, far, thresholdAtVal = lfw.evaluate(emb_array,
actual_issame, nrof_folds=args.lfw_nrof_folds)
print()
print('--- Verify using Euclidian distance ---')
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
#print('Accuracy array:', accuracy)
print('Best threshold: %1.3f' % bestThreshold)
print('Minimal threshold of hit rate @ 100%%: %1.3f' % minThreshold)
print('Maximum threshold of false alarm rate @ 0%%: %1.3f' % maxThreshold)
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
print('Threshold @ %1.3f' % thresholdAtVal)
auc = metrics.auc(fpr, tpr)
# plt.clf()
# plt.plot(fpr, tpr, '.')
# plt.savefig('euclidian_distance_auc.jpg')
print('Area Under Curve (AUC): %1.3f' % auc)
eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x), 0., 1.)
print('Equal Error Rate (EER): %1.3f' % eer)
tpr, fpr, accuracy, bestThreshold, minThreshold, maxThreshold, val, val_std, far, thresholdAtVal = lfw.evaluate(emb_array,
actual_issame, nrof_folds=args.lfw_nrof_folds, distance_metric=1)
print()
print("--- Verify using Cosine Similarity ---")
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
#print('Accuracy array:', accuracy)
print('Best threshold: %1.3f' % bestThreshold)
print('Minimal threshold of hit rate @ 100%%: %1.3f' % minThreshold)
print('Maximum threshold of false alarm rate @ 0%%: %1.3f' % maxThreshold)
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
print('Threshold @ %1.3f' % thresholdAtVal)
auc = metrics.auc(fpr, tpr)
# plt.clf()
# plt.plot(fpr, tpr, '.')
# plt.savefig('cosine_similarity_auc.jpg')
print('Area Under Curve (AUC): %1.3f' % auc)
eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x), 0., 1.)
print('Equal Error Rate (EER): %1.3f' % eer)
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):
#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):
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)
train_set_ID = facenet.get_dataset(args.data_dir_ID)
train_set_camera = facenet.get_dataset(args.data_dir_camera)
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)
# associative, fengchen
assoc = Associative(network, args)
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_ID = tf.placeholder(tf.string,
shape=(None, 3),
name='image_paths_ID')
image_paths_placeholder_camera = tf.placeholder(
tf.string, shape=(None, 3), name='image_paths_camera')
image_paths_placeholder_valid = tf.placeholder(
tf.string, shape=(None, 3), name='image_paths_valid')
labels_placeholder_ID = tf.placeholder(tf.int64,
shape=(None, 3),
name='labels_ID')
labels_placeholder_camera = tf.placeholder(tf.int64,
shape=(None, 3),
name='labels_camera')
labels_placeholder_valid = tf.placeholder(tf.int64,
shape=(None, 3),
name='labels_valid')
input_queue_ID = data_flow_ops.FIFOQueue(capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(3, ), (3, )],
shared_name=None,
name=None)
input_queue_camera = data_flow_ops.FIFOQueue(
capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(3, ), (3, )],
shared_name=None,
name=None)
input_queue_valid = data_flow_ops.FIFOQueue(
capacity=100000,
dtypes=[tf.string, tf.int64],
shapes=[(3, ), (3, )],
shared_name=None,
name=None)
enqueue_op_ID = input_queue_ID.enqueue_many(
[image_paths_placeholder_ID, labels_placeholder_ID])
enqueue_op_camera = input_queue_camera.enqueue_many(
[image_paths_placeholder_camera, labels_placeholder_camera])
enqueue_op_valid = input_queue_valid.enqueue_many(
[image_paths_placeholder_valid, labels_placeholder_valid])
nrof_preprocess_threads = 4
images_and_labels_ID = get_images_and_labels(nrof_preprocess_threads,
input_queue_ID)
images_and_labels_camera = get_images_and_labels(
nrof_preprocess_threads, input_queue_camera)
images_and_labels_valid = get_images_and_labels(
nrof_preprocess_threads, input_queue_valid)
image_batch_ID, labels_batch_ID = tf.train.batch_join(
images_and_labels_ID,
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_ID = tf.identity(image_batch_ID, 'image_batch_ID')
image_batch_ID = tf.identity(image_batch_ID, 'input_ID')
labels_batch_ID = tf.identity(labels_batch_ID, 'label_batch_ID')
image_batch_camera, labels_batch_camera = tf.train.batch_join(
images_and_labels_camera,
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_camera = tf.identity(image_batch_camera,
'image_batch_camera')
image_batch_camera = tf.identity(image_batch_camera, 'input_camera')
labels_batch_camera = tf.identity(labels_batch_camera,
'label_batch_camera')
image_batch_valid, labels_batch_valid = tf.train.batch_join(
images_and_labels_valid,
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_valid = tf.identity(image_batch_valid, 'image_batch_valid')
labels_batch_valid = tf.identity(labels_batch_valid,
'label_batch_valid')
image_paths_ID, _ = sample_people(train_set_ID,
args.people_per_batch_mmd,
args.images_per_person_mmd)
image_paths_camera, _ = sample_people(train_set_camera,
args.people_per_batch_mmd,
args.images_per_person_mmd)
images_mmd_ID = get_image_mmd(image_paths_ID)
images_mmd_camera = get_image_mmd(image_paths_camera)
# Build the inference graph
prelogits_ID, _, _, _, _ = network.inference(
image_batch_ID,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
prelogits_camera, _, _, _, _ = network.inference(
image_batch_camera,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
_, _, _, feature_map3_ID, _ = network.inference(
images_mmd_ID,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
_, _, _, feature_map3_camera, _ = network.inference(
images_mmd_camera,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
prelogits_valid, _, _, _, _ = network.inference(
image_batch_valid,
args.keep_probability,
phase_train=phase_train_placeholder,
bottleneck_layer_size=args.embedding_size,
weight_decay=args.weight_decay)
embeddings_ID = tf.nn.l2_normalize(prelogits_ID,
1,
1e-10,
name='embeddings_ID')
embeddings_camera = tf.nn.l2_normalize(prelogits_camera,
1,
1e-10,
name='embeddings_camera')
embeddings_valid = tf.nn.l2_normalize(prelogits_valid,
1,
1e-10,
name='embeddings_valid')
# Split embeddings into anchor, positive and negative and calculate triplet loss
anchor_ID, positive_ID, negative_ID = tf.unstack(
tf.reshape(embeddings_ID, [-1, 3, args.embedding_size]), 3, 1)
triplet_loss_ID = facenet.triplet_loss(anchor_ID, positive_ID,
negative_ID, args.alpha)
anchor_camera, positive_camera, negative_camera = tf.unstack(
tf.reshape(embeddings_camera, [-1, 3, args.embedding_size]), 3, 1)
triplet_loss_camera = facenet.triplet_loss(anchor_camera,
positive_camera,
negative_camera, 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)
# associative, fengchen
associative_loss = assoc.loss() * 10
# Calculate the total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
loss_feature_map3 = mmd_loss(feature_map3_ID, feature_map3_camera)
# loss_feature_map3 = 3*loss_feature_map3
triplet_loss = tf.add_n([triplet_loss_ID] + [triplet_loss_camera] +
regularization_losses,
name='triplet_loss')
loss_total = tf.add_n([triplet_loss_ID] + [triplet_loss_camera] +
[loss_feature_map3] + [associative_loss] +
regularization_losses,
name='loss_total')
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op = facenet.train(loss_total, global_step, args.optimizer,
learning_rate, args.moving_average_decay,
tf.global_variables())
train_op_triplet = facenet.train(triplet_loss, global_step,
args.optimizer, learning_rate,
args.moving_average_decay,
tf.global_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))
# 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 model: %s' % args.pretrained_model)
saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
saver.restore(sess, os.path.expanduser(args.pretrained_model))
saver = tf.train.Saver(tf.global_variables(), max_to_keep=3)
# 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_ID, train_set_camera, epoch,
image_paths_placeholder_ID,
image_paths_placeholder_camera, labels_placeholder_ID,
labels_placeholder_camera, labels_batch_ID,
labels_batch_camera, batch_size_placeholder,
learning_rate_placeholder, phase_train_placeholder,
enqueue_op_ID, enqueue_op_camera, global_step,
embeddings_ID, embeddings_camera, triplet_loss,
loss_total, triplet_loss_ID, triplet_loss_camera,
loss_feature_map3, associative_loss,
regularization_losses, train_op, train_op_triplet,
summary_writer, args.learning_rate_schedule_file,
args.embedding_size)
# 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_valid,
labels_batch_valid, image_paths_placeholder_valid,
labels_placeholder_valid, batch_size_placeholder,
learning_rate_placeholder,
phase_train_placeholder, enqueue_op_valid,
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, '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 test(args):
with tf.Graph().as_default():
with tf.Session() as sess:
#saver = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
saver = tf.train.Saver(tf.global_variables())
saver.restore(sess, args.model)
# Read the file containing the pairs used for testing
pairs = lfw.read_pairs(os.path.expanduser(args.test_list_dir))
# Get the paths for the corresponding images
paths, actual_issame = lfw.get_paths(
os.path.expanduser(args.test_data_dir), pairs,
args.test_list_dir)
image_size = args.image_size
print('image size', image_size)
images_placeholder = tf.placeholder(tf.float32,
shape=(None, args.image_height,
args.image_width,
args.image_width),
name='image')
phase_train_placeholder = tf.placeholder(tf.bool,
name='phase_train')
#network definition.
prelogits1 = network.infer(images_placeholder, args.embedding_size)
if args.fc_bn:
print('do batch norm after network')
prelogits = slim.batch_norm(
prelogits1,
is_training=phase_train_placeholder,
epsilon=1e-5,
scale=True,
scope='softmax_bn')
#embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
embeddings = tf.identity(prelogits)
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on testing images')
batch_size = args.test_batch_size
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0 * nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches):
start_index = i * batch_size
print('handing {}/{}'.format(start_index, nrof_images))
end_index = min((i + 1) * batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = utils.load_data(paths_batch, False, False, args.image_height,args.image_width,False,\
(args.image_height,args.image_width))
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
feats, a = sess.run([embeddings, prelogits],
feed_dict=feed_dict)
# do not know for sure whether we should turn this on? it depends.
feats = utils.l2_normalize(feats)
emb_array[start_index:end_index, :] = feats
tpr, fpr, accuracy, val, val_std, far = lfw.evaluate(
emb_array,
actual_issame,
0.001,
nrof_folds=args.test_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))
auc = metrics.auc(fpr, tpr)
print('Area Under Curve (AUC): %1.3f' % auc) #
eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr, tpr)(x),
0., 1.) #fill_value="extrapolate"
print('Equal Error Rate (EER): %1.3f' % eer)
tpr1, fpr1, accuracy1, val1, val_std1, far1 = lfw.evaluate(
emb_array,
actual_issame,
0.0001,
nrof_folds=args.test_nrof_folds)
print('Accuracy: %1.3f+-%1.3f' %
(np.mean(accuracy1), np.std(accuracy1)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' %
(val1, val_std1, far1))
auc = metrics.auc(fpr1, tpr1)
print('Area Under Curve (AUC): %1.3f' % auc) #
eer = brentq(lambda x: 1. - x - interpolate.interp1d(fpr1, tpr1)
(x), 0., 1.) #fill_value="extrapolate"
print('Equal Error Rate (EER): %1.3f' % eer)
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):
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 train_net(args):
ctx = []
cvd = os.environ['CUDA_VISIBLE_DEVICES'].strip()
if len(cvd)>0:
for i in xrange(len(cvd.split(','))):
ctx.append(mx.gpu(i))
if len(ctx)==0:
ctx = [mx.cpu()]
print('use cpu')
else:
print('gpu num:', len(ctx))
prefix = args.prefix
end_epoch = args.end_epoch
pretrained = '../model/resnet-152'
load_epoch = args.load_epoch
args.image_size = 160
per_batch_size = 60
args.ctx_num = len(ctx)
args.batch_size = per_batch_size*args.ctx_num
#args.all_batch_size = args.batch_size*args.ctx_num
args.bag_size = 3600
args.margin = 0.2
args.num_classes = 10575 #webface
data_shape = (3,args.image_size,args.image_size)
begin_epoch = 0
base_lr = 0.05
base_wd = 0.0002
base_mom = 0.0
lr_decay = 0.98
if not args.retrain:
#load and initialize params
print(pretrained)
_, arg_params, aux_params = mx.model.load_checkpoint(pretrained, load_epoch)
sym, arg_params, aux_params = get_symbol(args, arg_params, aux_params)
#arg_params, aux_params = load_param(pretrained, epoch, convert=True)
data_shape_dict = {'data': (args.batch_size, 3, args.image_size, args.image_size), 'softmax_label': (args.batch_size,)}
resnet_dcn.init_weights(sym, data_shape_dict, arg_params, aux_params)
else:
pretrained = args.prefix
sym, arg_params, aux_params = mx.model.load_checkpoint(pretrained, load_epoch)
begin_epoch = load_epoch
end_epoch = begin_epoch+10
base_wd = 0.00005
lr_decay = 0.5
base_lr = 0.015
# infer max shape
model = mx.mod.Module(
context = ctx,
symbol = sym,
#label_names = [],
#fixed_param_prefix = fixed_param_prefix,
)
train_dataiter = FaceIter(
path_imglist = "/raid5data/dplearn/faceinsight_align_webface.lst",
data_shape = data_shape,
mod = model,
ctx_num = args.ctx_num,
batch_size = args.batch_size,
bag_size = args.bag_size,
images_per_person = 5,
)
#_dice = DiceMetric()
_acc = AccMetric()
eval_metrics = [mx.metric.create(_acc)]
# rpn_eval_metric, rpn_cls_metric, rpn_bbox_metric, eval_metric, cls_metric, bbox_metric
#for child_metric in [fcn_loss_metric]:
# eval_metrics.add(child_metric)
# callback
#batch_end_callback = callback.Speedometer(input_batch_size, frequent=args.frequent)
#epoch_end_callback = mx.callback.module_checkpoint(mod, prefix, period=1, save_optimizer_states=True)
# decide learning rate
#lr_step = '10,20,30'
#train_size = 4848
#nrof_batch_in_epoch = int(train_size/input_batch_size)
#print('nrof_batch_in_epoch:', nrof_batch_in_epoch)
#lr_factor = 0.1
#lr_epoch = [float(epoch) for epoch in lr_step.split(',')]
#lr_epoch_diff = [epoch - begin_epoch for epoch in lr_epoch if epoch > begin_epoch]
#lr = base_lr * (lr_factor ** (len(lr_epoch) - len(lr_epoch_diff)))
#lr_iters = [int(epoch * train_size / batch_size) for epoch in lr_epoch_diff]
#print 'lr', lr, 'lr_epoch_diff', lr_epoch_diff, 'lr_iters', lr_iters
#lr_scheduler = MultiFactorScheduler(lr_iters, lr_factor)
# optimizer
#optimizer_params = {'momentum': 0.9,
# 'wd': 0.0005,
# 'learning_rate': base_lr,
# 'rescale_grad': 1.0,
# 'clip_gradient': None}
initializer = mx.init.Xavier(rnd_type='gaussian', factor_type="in", magnitude=2)
#opt = optimizer.SGD(learning_rate=base_lr, momentum=0.9, wd=base_wd, rescale_grad=(1.0/args.batch_size))
opt = optimizer.SGD(learning_rate=base_lr, momentum=base_mom, wd=base_wd, rescale_grad=1.0)
#opt = optimizer.AdaGrad(learning_rate=base_lr, wd=base_wd, rescale_grad=1.0)
_cb = mx.callback.Speedometer(args.batch_size, 10)
lfw_dir = '/raid5data/dplearn/lfw_mtcnn'
lfw_pairs = lfw.read_pairs(os.path.join(lfw_dir, 'pairs.txt'))
lfw_paths, issame_list = lfw.get_paths(lfw_dir, lfw_pairs, 'png')
imgs = []
lfw_data_list = []
for flip in [0,1]:
lfw_data = nd.empty((len(lfw_paths), 3, args.image_size, args.image_size))
i = 0
for path in lfw_paths:
with open(path, 'rb') as fin:
_bin = fin.read()
img = mx.image.imdecode(_bin)
img = nd.transpose(img, axes=(2, 0, 1))
if flip==1:
img = img.asnumpy()
for c in xrange(img.shape[0]):
img[c,:,:] = np.fliplr(img[c,:,:])
img = nd.array( img )
#print(img.shape)
lfw_data[i][:] = img
i+=1
if i%1000==0:
print('loading lfw', i)
print(lfw_data.shape)
lfw_data_list.append(lfw_data)
def lfw_test(nbatch):
print('testing lfw..')
embeddings_list = []
for i in xrange( len(lfw_data_list) ):
lfw_data = lfw_data_list[i]
embeddings = None
ba = 0
while ba<lfw_data.shape[0]:
bb = min(ba+args.batch_size, lfw_data.shape[0])
_data = nd.slice_axis(lfw_data, axis=0, begin=ba, end=bb)
_label = nd.ones( (bb-ba,) )
db = mx.io.DataBatch(data=(_data,), label=(_label,))
model.forward(db, is_train=False)
net_out = model.get_outputs()
_embeddings = net_out[0].asnumpy()
if embeddings is None:
embeddings = np.zeros( (lfw_data.shape[0], _embeddings.shape[1]) )
embeddings[ba:bb,:] = _embeddings
ba = bb
embeddings_list.append(embeddings)
acc_list = []
embeddings = embeddings_list[0]
_, _, accuracy, val, val_std, far = lfw.evaluate(embeddings, issame_list, nrof_folds=10)
acc_list.append(np.mean(accuracy))
print('[%d]Accuracy: %1.3f+-%1.3f' % (nbatch, np.mean(accuracy), np.std(accuracy)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
embeddings = np.concatenate(embeddings_list, axis=1)
embeddings = sklearn.preprocessing.normalize(embeddings)
print(embeddings.shape)
_, _, accuracy, val, val_std, far = lfw.evaluate(embeddings, issame_list, nrof_folds=10)
acc_list.append(np.mean(accuracy))
print('[%d]Accuracy-Flip: %1.3f+-%1.3f' % (nbatch, np.mean(accuracy), np.std(accuracy)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
pca = PCA(n_components=128)
embeddings = pca.fit_transform(embeddings)
embeddings = sklearn.preprocessing.normalize(embeddings)
print(embeddings.shape)
_, _, accuracy, val, val_std, far = lfw.evaluate(embeddings, issame_list, nrof_folds=10)
acc_list.append(np.mean(accuracy))
print('[%d]Accuracy-PCA: %1.3f+-%1.3f' % (nbatch, np.mean(accuracy), np.std(accuracy)))
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
return max(*acc_list)
#global_step = 0
highest_acc = [0.0]
last_save_acc = [0.0]
def _batch_callback(param):
#global global_step
mbatch = param.nbatch+1
if mbatch % 4000 == 0:
opt.lr *= lr_decay
#print(param.nbatch, opt.lr)
_cb(param)
if param.nbatch%100==0:
print('lr-batch-epoch:',opt.lr,param.nbatch,param.epoch)
if param.nbatch>=0 and param.nbatch%400==0:
acc = lfw_test(param.nbatch)
if acc>highest_acc[0]:
highest_acc[0] = acc
if acc>0.9 and acc-last_save_acc[0]>=0.01:
print('saving', mbatch, acc, last_save_acc[0])
_arg, _aux = model.get_params()
mx.model.save_checkpoint(args.prefix, mbatch, model.symbol, _arg, _aux)
last_save_acc[0] = acc
print('[%d]highest Accu: %1.3f'%(param.nbatch, highest_acc[0]))
sys.stdout.flush()
sys.stderr.flush()
epoch_cb = mx.callback.do_checkpoint(prefix, 1)
#epoch_cb = None
def _epoch_callback(epoch, sym, arg_params, aux_params):
print('epoch-end', epoch)
model.fit(train_dataiter,
begin_epoch = begin_epoch,
num_epoch = end_epoch,
#eval_data = val_dataiter,
eval_metric = eval_metrics,
kvstore = 'device',
optimizer = opt,
#optimizer_params = optimizer_params,
initializer = initializer,
arg_params = arg_params,
aux_params = aux_params,
allow_missing = True,
batch_end_callback = _batch_callback,
epoch_end_callback = epoch_cb )
def main(args):
with tf.Graph().as_default():
with tf.Session() as sess:
# Load model
model = AttributeModel()
# Convert to classifier
model.convert_to_classifier()
# Load images paths and labels
pairs = lfw.read_pairs(args.lfw_pairs)
paths, true_issame = lfw.get_paths(args.lfw_dir, pairs)
path1_all = paths[0::2]
path2_all = paths[1::2]
labels_all = 1 * np.array(
true_issame
) # (N, ) array of 0 of 1, N = 6000 for LFW view2 dataset
# NOTE! for this example, 1: identical, 0: different
k_fold = KFold(n_splits=10,
shuffle=False) # 10-fold cross validation
indices = np.arange(np.shape(path1_all)[0])
real_labels = []
adversarial_labels = []
labels_evaluated = []
for ith_fold, (_, fold_idx) in enumerate(k_fold.split(indices)):
if ith_fold == args.lfw_nrof_folds:
break
fold_idx = np.append(fold_idx[:50], fold_idx[-50:])
path1 = [path1_all[i] for i in fold_idx]
path2 = [path2_all[i] for i in fold_idx]
labels_evaluated = np.append(labels_evaluated,
[labels_all[i] for i in fold_idx],
axis=-1)
# labels = labels_all[fold_idx]
num_images = len(path1)
num_batches = int(
math.ceil(1.0 * num_images / args.lfw_batch_size))
for i in range(num_batches):
start_idx = i * args.lfw_batch_size
end_idx = min((i + 1) * args.lfw_batch_size, num_images)
path1_batch = path1[start_idx:end_idx]
path2_batch = path2[start_idx:end_idx]
# labels_batch = to_categorical(labels[start_idx:end_idx], num_classes=2)
# Load pairs of faces and their labels in one-hot encoding
adv_faces, target_faces = load_images(
path1_batch, path2_batch)
# Create target embeddings using Facenet itself
feed_dict = {
model.face_input: target_faces
} #, model.phase_train: False}
target_embeddings = sess.run(model.embedding_output,
feed_dict=feed_dict)
# Run attack
feed_dict = {
model.face_input: adv_faces,
model.victim_embedding_input: target_embeddings
} #,
#model.batch_size: 10, model.phase_train: False}
adv_x = prepare_attack(sess, args, model, adv_faces,
target_embeddings)
real_labels_batch, adversarial_labels_batch = run_attack(
sess, model, adv_x, feed_dict)
"""
# Define input TF placeholder
x = tf.placeholder(tf.float32, shape=(None, 160, 160, 3), name='x')
y = tf.placeholder(tf.float32, shape=(None, 2), name='y')
preds = model.softmax_output
# Evaluate the accuracy on legitimate test examples
feed_dict = {model.face_input: adv_faces, model.victim_embedding_input: target_embeddings,
model.batch_size: 10, model.phase_train: False}
accur = model_eval(sess, x, y, preds, adv_faces, labels_batch,
feed=feed_dict, args={'batch_size': args.lfw_batch_size})
# Perform attack
model.face_input.set_shape(np.shape(adv_faces))
cw = CarliniWagnerL2(model, sess)
cw_params = {'binary_search_steps': 1,
'max_iterations': 100,
'learning_rate': .2,
'batch_size': args.lfw_batch_size,
'initial_const': 10}
adv_x = cw.generate(model.face_input, feed_dict, **cw_params)
adv = sess.run(adv_x, feed_dict)
feed_dict_adv = {model.face_input: adv, model.victim_embedding_input: target_embeddings,
model.batch_size: 10, model.phase_train: False}
accur = model_eval(sess, x, y, preds, adv, labels_batch,
feed=feed_dict, args={'batch_size': args.lfw_batch_size})
"""
# Evaluate accuracy
real_labels = np.append(
real_labels, np.argmax(real_labels_batch, axis=-1))
adversarial_labels = np.append(
adversarial_labels,
np.argmax(adversarial_labels_batch, axis=-1))
# Compute accuracy
evaluate(labels_evaluated, real_labels, adversarial_labels)
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)
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)
with tf.Graph().as_default():
tf.set_random_seed(args.seed) # TODO: NEED TO KNOW WHY IS NEEDED !
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_jpeg(file_contents, channels=3)
# 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 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())
# 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 model: %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
print('========= STARTING... SAVE MODEL ==========')
save_variables_and_metagraph(sess, saver, summary_writer,
model_dir, subdir, step)
print('========= MODEL SAVED, NEXT EPOCH ==========')
# 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, '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)
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' % len(train_set))
print('Total number of examples: %d' % len(image_list))
# Placeholder for the learning rate
learning_rate_placeholder = tf.placeholder(tf.float32, name='learning_rate')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
prelogits, _ = network.inference(image_batch, args.keep_probability,
phase_train=phase_train_placeholder, weight_decay=args.weight_decay)
with tf.variable_scope('Logits'):
n = int(prelogits.get_shape()[1])
m = len(train_set)
w = tf.get_variable('w', shape=[n,m], dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.1),
regularizer=slim.l2_regularizer(args.weight_decay),
trainable=True)
b = tf.get_variable('b', [m], initializer=None, trainable=True)
logits = tf.matmul(prelogits, w) + b
# 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)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
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())
# Create a saver
save_variables = list(set(tf.trainable_variables())-set([w])-set([b]))
saver = tf.train.Saver(save_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:
saver.restore(sess, 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, epoch, phase_train_placeholder, learning_rate_placeholder, global_step,
total_loss, train_op, summary_op, summary_writer, regularization_losses, args.learning_rate_schedule_file)
# Evaluate on LFW
if args.lfw_dir:
start_time = time.time()
_, _, accuracy, val, val_std, far = lfw.validate(sess, lfw_paths, actual_issame, args.seed,
args.batch_size, image_batch, 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))
lfw_time = time.time() - start_time
# 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.value.add(tag='time/lfw', simple_value=lfw_time)
summary_writer.add_summary(summary, step)
with open(os.path.join(log_dir,'lfw_result.txt'),'at') as f:
f.write('%d\t%.5f\t%.5f\n' % (step, np.mean(accuracy), val))
# Save variables and the metagraph if it doesn't exist already
save_variables_and_metagraph(sess, saver, summary_writer, model_dir, step)
return model_dir
