def train():
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, test_set = facenet.split_dataset(dataset, 0.9)
fileName = "/home/david/debug4.h5"
f = h5py.File(fileName, "r")
for item in f.values():
print(item)
w1 = f['1w'][:]
b1 = f['1b'][:]
f.close()
print(w1.shape)
print(b1.shape)
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, 96, 96, 3), name='Input')
# Build a Graph that computes the logits predictions from the inference model
#embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, phase_train=True)
conv1 = _conv(images_placeholder, 3, 64, 7, 7, 2, 2, 'SAME', 'conv1_7x7', phase_train=False, use_batch_norm=False, init_weight=w1, init_bias=b1)
resh1 = tf.reshape(conv1, [-1, 294912])
embeddings = _affine(resh1, 294912, 128)
# Split example embeddings into anchor, positive and negative
a, p, n = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(a, p, n)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, grads = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def)
epoch = 0
with sess.as_default():
while epoch<FLAGS.max_nrof_epochs:
batch_number = 0
while batch_number<FLAGS.epoch_size:
print('Loading new data')
image_data, num_per_class, image_paths = facenet.load_data(train_set)
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = FLAGS.people_per_batch*FLAGS.images_per_person
nrof_batches_per_epoch = int(np.floor(nrof_examples_per_epoch/FLAGS.batch_size))
if True:
for i in xrange(nrof_batches_per_epoch):
feed_dict, _ = facenet.get_batch(images_placeholder, image_data, i)
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Select triplets based on the embeddings
apn, nrof_random_negs, nrof_triplets = facenet.select_triplets(emb_array, num_per_class, image_data)
duration = time.time() - start_time
print('(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' % (nrof_random_negs, nrof_triplets, duration))
count = 0
while count<nrof_triplets*3 and batch_number<FLAGS.epoch_size:
start_time = time.time()
feed_dict, batch = facenet.get_batch(images_placeholder, apn, batch_number)
if (batch_number%20==0):
err, summary_str, _ = sess.run([loss, summary_op, train_op], feed_dict=feed_dict)
summary_writer.add_summary(summary_str, FLAGS.epoch_size*epoch+batch_number)
else:
err, _ = sess.run([loss, train_op], feed_dict=feed_dict)
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f' % (epoch, batch_number, FLAGS.epoch_size, duration, err))
batch_number+=1
count+=FLAGS.batch_size
else:
while batch_number<FLAGS.epoch_size:
start_time = time.time()
feed_dict, _ = facenet.get_batch(images_placeholder, image_data, batch_number)
grad_tensors, grad_vars = zip(*grads)
eval_list = (train_op, loss) + grad_tensors
result = sess.run(eval_list, feed_dict=feed_dict)
grads_eval = result[2:]
nrof_parameters = 0
for gt, gv in zip(grads_eval, grad_vars):
print('%40s: %6d' % (gv.op.name, np.size(gt)))
nrof_parameters += np.size(gt)
print('Total number of parameters: %d' % nrof_parameters)
err = result[1]
batch_number+=1
epoch+=1
# Save the model checkpoint periodically.
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=epoch*FLAGS.epoch_size+batch_number)
def main(args):
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(argv=None): # pylint: disable=unused-argument
if FLAGS.model_name:
subdir = FLAGS.model_name
preload_model = True
else:
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
preload_model = False
log_dir = os.path.join(os.path.expanduser(FLAGS.logs_base_dir), subdir)
model_dir = os.path.join(os.path.expanduser(FLAGS.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.mkdir(model_dir)
np.random.seed(seed=FLAGS.seed)
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, validation_set = facenet.split_dataset(dataset, FLAGS.train_set_fraction, FLAGS.split_mode)
print('Model directory: %s' % model_dir)
with tf.Graph().as_default():
tf.set_random_seed(FLAGS.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, FLAGS.image_size, FLAGS.image_size, 3),
name='input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, phase_train=phase_train_placeholder)
# Split example embeddings into anchor, positive and negative
anchor, positive, negative = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(anchor, positive, negative)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, _ = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=0)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
with sess.as_default():
if preload_model:
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Training and validation loop
for epoch in range(FLAGS.max_nrof_epochs):
# Train for one epoch
step = train(sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Validate epoch
validate(sess, validation_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Save the model checkpoint after each epoch
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
graphdef_dir = os.path.join(model_dir, 'graphdef')
graphdef_filename = 'graph_def.pb'
if (not os.path.exists(os.path.join(graphdef_dir, graphdef_filename))):
print('Saving graph definition')
tf.train.write_graph(sess.graph_def, graphdef_dir, graphdef_filename, False)
def main(args):
network = importlib.import_module(args.model_def)
image_size = (args.image_size, args.image_size)
subdir = datetime.strftime(
datetime.now(), '%Y-%m-%d-%H-softmax-' +
args.model_def.split(".")[-1] + "-" + args.data_dir.split("/")[-1])
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)
ckpt = tf.train.get_checkpoint_state(pretrained_model)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
# 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_valrate2':
np.zeros((args.max_nrof_epochs, ), np.float32),
'lfw_valrate3':
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.items():
f.create_dataset(key, data=value)
return model_dir
def main(args):
network = importlib.import_module(args.model_def)
image_size = (args.image_size, args.image_size)
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
log_dir = os.path.join(os.path.expanduser(args.logs_base_dir),
subdir) #日志保存地址
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
# os.path.realpath(__file__)代表返回当前模块真实路径
# os.path.split(os.path.realpath(__file__))代表返回路径的目录和文件名(元组形式)
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是列表，列表元素为每一个类的ImageClass对象，定义见facenet.py文件
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)
# 划分训练集和测试集，train_set和val_set的形式和dataset一样
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(即有多少人)
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也是列表，子元素也是列表，每个子列表包含pairs.txt的每一行
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对应的是全局批的个数，根据这个参数可以更新学习率
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)
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的大小和样本个数一样
range_size = array_ops.shape(labels)[0]
#QueueRunner：保存的是队列中的入列操作，保存在一个list当中，其中每个enqueue运行在一个线程当中
#range_input_producer：返回的是一个队列，队列中有打乱的整数，范围是从0到range size
#range_size大小和总的样本个数一样
#并将一个QueueRunner添加到当前图的QUEUE_RUNNER集合中
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
# 返回的是一个出列操作，每次出列一个epoch需要用到的样本个数
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')
# 上面的队列是一个样本索引的出队队列，只用来出列
# 用来每次出列一个epoch中用到的样本
# 这里是第二个队列，这个队列用来入列，每个元素的大小为shape=[(1,),(1,),(1,)]
nrof_preprocess_threads = 4
# 这里的shape代表每一个元素的维度
input_queue = data_flow_ops.FIFOQueue(
capacity=600000,
dtypes=[tf.string, tf.int32, tf.int32],
shapes=[(1, ), (1, ), (1, )],
shared_name=None,
name=None)
# 这时一个入列的操作，这个操作将在session run的时候用到
# 每次入列的是image_paths_placeholder, labels_placeholder对
# 注意，这里只有2个队列，一个用来出列打乱的元素序号
# 一个根据对应的需要读取指定的文件
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('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')
# arcface_logits = arcface_logits_compute(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)
with tf.variable_scope('Logits'):
arcface_logits = arcface_logits_compute(embeddings, label_batch,
args, nrof_classes)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=label_batch,
logits=arcface_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(arcface_logits, 1),
tf.cast(label_batch, tf.int64)), tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
# for weights in slim.get_variables_by_name('embedding_weights'):
# weight_regularization = tf.contrib.layers.l2_regularizer(args.weight_decay)(weights)
# tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, weight_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')
#define two saver in case under 'finetuning on different dataset' situation
saver_save = tf.train.Saver(tf.trainable_variables(), max_to_keep=3)
train_op = facenet.train(total_loss, global_step, args.optimizer,
learning_rate, args.moving_average_decay,
tf.global_variables(), args.log_histograms)
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)
facenet.load_model(pretrained_model)
print('Running arcface training')
best_accuracy = 0.0
for epoch in range(1, args.max_nrof_epochs + 1):
step = sess.run(global_step, feed_dict=None)
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,
global_step, total_loss, accuracy, train_op, summary_op,
summary_writer, regularization_losses,
args.learning_rate_schedule_file, args.random_rotate,
args.random_crop, args.random_flip,
args.use_fixed_image_standardization, control_placeholder)
if not cont:
break
print('validation running...')
if args.lfw_dir:
best_accuracy = 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, best_accuracy, saver_save,
model_dir, subdir, args.lfw_subtract_mean,
args.lfw_use_flipped_images,
args.use_fixed_image_standardization,
args.lfw_distance_metric)
return model_dir
def main(argv=None): # pylint: disable=unused-argument
if FLAGS.model_name:
subdir = FLAGS.model_name
preload_model = True
else:
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
preload_model = False
log_dir = os.path.join(os.path.expanduser(FLAGS.logs_base_dir), subdir)
if not os.path.isdir(log_dir): # Create the log directory if it doesn't exist
os.mkdir(log_dir)
model_dir = os.path.join(os.path.expanduser(FLAGS.models_base_dir), subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.mkdir(model_dir)
# Store some git revision info in a text file in the log directory
src_path,_ = os.path.split(os.path.realpath(__file__))
facenet.store_revision_info(src_path, log_dir, ' '.join(argv))
np.random.seed(seed=FLAGS.seed)
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, validation_set = facenet.split_dataset(dataset, FLAGS.train_set_fraction, FLAGS.split_mode)
print('Model directory: %s' % model_dir)
with tf.Graph().as_default():
tf.set_random_seed(FLAGS.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(None, FLAGS.image_size, FLAGS.image_size, 3), name='input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
embeddings = network.inference(images_placeholder, FLAGS.pool_type, FLAGS.use_lrn,
FLAGS.keep_probability, phase_train=phase_train_placeholder)
# Split example embeddings into anchor, positive and negative
anchor, positive, negative = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(anchor, positive, negative, FLAGS.alpha)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, _ = facenet.train(loss, global_step, FLAGS.optimizer, FLAGS.learning_rate, FLAGS.moving_average_decay)
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=0)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(log_dir, sess.graph)
with sess.as_default():
if preload_model:
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Training and validation loop
for epoch in range(FLAGS.max_nrof_epochs):
# Train for one epoch
step = train(sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Store the state of the random number generator
rng_state = np.random.get_state()
# Test on validation set
np.random.seed(seed=FLAGS.seed)
validate(sess, validation_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, 'validation', summary_writer)
# Test on training set
np.random.seed(seed=FLAGS.seed)
validate(sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, 'training', summary_writer)
# Restore state of the random number generator
np.random.set_state(rng_state)
if (epoch % FLAGS.checkpoint_period == 0) or (epoch==FLAGS.max_nrof_epochs-1):
# Save the model checkpoint
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def main(argv=None): # pylint: disable=unused-argument
if FLAGS.model_name:
subdir = FLAGS.model_name
preload_model = True
else:
subdir = datetime.strftime(datetime.now(), '%Y%m%d-%H%M%S')
preload_model = False
log_dir = os.path.join(FLAGS.logs_base_dir, subdir)
model_dir = os.path.join(FLAGS.models_base_dir, subdir)
if not os.path.isdir(model_dir): # Create the model directory if it doesn't exist
os.mkdir(model_dir)
np.random.seed(seed=FLAGS.seed)
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, validation_set = facenet.split_dataset(dataset, FLAGS.train_set_fraction)
with tf.Graph().as_default():
tf.set_random_seed(FLAGS.seed)
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, FLAGS.image_size, FLAGS.image_size, 3),
name='Input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, phase_train=phase_train_placeholder)
# Split example embeddings into anchor, positive and negative
anchor, positive, negative = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(anchor, positive, negative)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, grads = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables(), max_to_keep=0)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(log_dir, graph_def=sess.graph_def)
with sess.as_default():
if preload_model:
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Training and validation loop
for epoch in range(FLAGS.max_nrof_epochs):
# Train for one epoch
step = train(sess, train_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Validate epoch
validate(sess, validation_set, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer)
# Save the model checkpoint after each epoch
print('Saving checkpoint')
checkpoint_path = os.path.join(model_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
graphdef_dir = os.path.join(model_dir, 'graphdef')
graphdef_filename = 'graph_def.pb'
if (not os.path.exists(os.path.join(graphdef_dir, graphdef_filename))):
print('Saving graph definition')
tf.train.write_graph(sess.graph_def, graphdef_dir, graphdef_filename, False)
def main(args):
# 模型，定义在inception_resnet_v1 V2里（）， --model_def models.inception_resnet_v1
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
# 训练数据
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
assert len(image_list)>0, 'The training set should not be empty'
# 测试数据
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
# tf.convert_to_tensor用于将不同数据变成张量：比如可以让数组变成张量、也可以让列表变成张量。
labels = ops.convert_to_tensor(label_list, dtype=tf.int32)
range_size = array_ops.shape(labels)[0]
# 多线程读取数据，shuffle=True表示不是按顺序存储，可以随机获取，并一直循环。
# https://blog.csdn.net/lyg5623/article/details/69387917
index_queue = tf.train.range_input_producer(range_size, num_epochs=None,
shuffle=True, seed=None, capacity=32)
# epoch 大数据时迭代完一轮时次数，少量数据应该epoch = 全部数据个数/batch
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)
# 因为模型输出的(bottleneck_layer_size）没有计算最后一层(映射到图片类型)，这里计算最后一层
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)
# 按行进行泛化，行的平方求和再求平方根，得到的值按行除每个行的元素，对深度层面泛化? interface里最后一层输出为128个节点，slim.fully_connected(net, bottleneck_layer_size, activation_fn=None,
#https://blog.csdn.net/abiggg/article/details/79368982
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# 计算loss函数，当然还有其它训练参数也会加到这里来，通过比训练过程中一个weight加到正则化参数里来tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, weight)
# 模型中最后会把这个加到优化的loss中来。
#L= L_softmax + λL_cneter = Softmax(W_i + b_yj) + λ1/2||f(x_i) - c_yj ||_2^2
# 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))
# 模型中最后输出(bottleneck_layer_size每个类型的输出值的个数)的平均值加到正则化loss中，但prelogits_norm_loss_factor貌似为0
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_norm * args.prelogits_norm_loss_factor)
# 计算中心损失及增加的正则化loss中
# 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
# 计算预测损失，和上面框架的Softmax(W_i + b_yj)
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')
# 预测损失平均值加到losses变量中
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)
#计算总损失，cross_entropy_mean + 前面增加的一些正则化损失(包括模型中增加的)，通过tf.GraphKeys.REGULARIZATION_LOSSES获取出来
# 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()
# 训练模型
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
# 在测试数据上计算正确率
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.items():
f.create_dataset(key, data=value)
return model_dir
