def main():
align = align_dlib.AlignDlib(os.path.expanduser(FLAGS.dlib_face_predictor))
batch_size = 2
image_paths = [FLAGS.image1, FLAGS.image2]
landmarkIndices = align_dlib.AlignDlib.OUTER_EYES_AND_NOSE
with tf.Graph().as_default():
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(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, FLAGS.pool_type, FLAGS.use_lrn,
1.0, phase_train=phase_train_placeholder)
# Create a saver for restoring variable averages
ema = tf.train.ExponentialMovingAverage(1.0)
saver = tf.train.Saver(ema.variables_to_restore())
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(os.path.expanduser(FLAGS.model_dir))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
images = load_and_align_data(image_paths, FLAGS.image_size, align, landmarkIndices)
feed_dict = { images_placeholder: images, phase_train_placeholder: False }
emb = sess.run(embeddings, feed_dict=feed_dict)
dist = np.sqrt(np.mean(np.square(np.subtract(emb[0,:], emb[1,:]))))
print('Distance between the embeddings: %3.6f' % dist)
def main():
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
with tf.Graph().as_default():
# Creates graph from saved GraphDef
# NOTE: This does not work at the moment. Needs tensorflow to store variables in the graph_def.
# graphdef_filename = os.path.join(os.path.expanduser(FLAGS.model_dir), 'graphdef', 'graph_def.pb')
# with gfile.FastGFile(graphdef_filename, 'rb') as f:
# graph_def = tf.GraphDef()
# graph_def.ParseFromString(f.read())
# images_placeholder, phase_train_placeholder, embeddings = tf.import_graph_def(graph_def, return_elements = ['input', 'phase_train', 'embeddings'], name='')
# 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, FLAGS.pool_type, FLAGS.use_lrn,
1.0, phase_train=phase_train_placeholder)
# Create a saver for restoring variable averages
ema = tf.train.ExponentialMovingAverage(1.0)
saver = tf.train.Saver(ema.variables_to_restore())
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(os.path.expanduser(FLAGS.model_dir))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
nrof_images = len(paths)
nrof_batches = int(nrof_images / FLAGS.batch_size) # Run forward pass on the remainder in the last batch
emb_list = []
for i in range(nrof_batches):
start_time = time.time()
paths_batch = paths[i*FLAGS.batch_size:(i+1)*FLAGS.batch_size]
images = facenet.load_data(paths_batch, False, False, FLAGS.image_size)
feed_dict = { images_placeholder: images, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
duration = time.time() - start_time
print('Calculated embeddings for batch %d of %d: time=%.3f seconds' % (i+1,nrof_batches, duration))
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, np.asarray(actual_issame), FLAGS.seed)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
facenet.plot_roc(fpr, tpr, 'NN4')
def main():
align = align_dlib.AlignDlib(os.path.expanduser(FLAGS.dlib_face_predictor))
batch_size = 2
image_paths = [FLAGS.image1, FLAGS.image2]
landmarkIndices = align_dlib.AlignDlib.OUTER_EYES_AND_NOSE
with tf.Graph().as_default():
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32,
shape=(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,
FLAGS.pool_type,
FLAGS.use_lrn,
1.0,
phase_train=phase_train_placeholder)
# Create a saver for restoring variable averages
ema = tf.train.ExponentialMovingAverage(1.0)
saver = tf.train.Saver(ema.variables_to_restore())
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(
os.path.expanduser(FLAGS.model_dir))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
images = load_and_align_data(image_paths, FLAGS.image_size, align,
landmarkIndices)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb = sess.run(embeddings, feed_dict=feed_dict)
dist = np.sqrt(
np.mean(np.square(np.subtract(emb[0, :], emb[1, :]))))
print('Distance between the embeddings: %3.6f' % dist)
def main():
# Creates graph from saved GraphDef
# NOTE: This does not work at the moment. Needs tensorflow to store variables in the graph_def.
#create_graph(os.path.join(FLAGS.model_dir, 'graphdef', 'graph_def.pb'))
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
mpl.interactive(True)
with tf.Graph().as_default():
# 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)
# Create a saver for restoring variable averages
ema = tf.train.ExponentialMovingAverage(1.0)
saver = tf.train.Saver(ema.variables_to_restore())
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(os.path.expanduser(FLAGS.model_dir))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Run test on LFW to check accuracy for different horizontal/vertical translations of input images
if True:
offsets = np.arange(-30, 31, 3)
horizontal_offset_accuracy = [None] * len(offsets)
for idx, offset in enumerate(offsets):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, embeddings, paths, actual_issame, translate_images, (offset,0))
print('Hoffset: %1.3f Accuracy: %1.3f%c%1.3f' % (offset, np.mean(accuracy), u"\u00B1", 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, embeddings, paths, actual_issame, translate_images, (0,offset))
print('Voffset: %1.3f Accuracy: %1.3f%c%1.3f' % (offset, np.mean(accuracy), u"\u00B1", 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()
result_dir = os.path.expanduser(FLAGS.model_dir)
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 True:
angles = np.arange(-30, 31, 3)
rotation_accuracy = [None] * len(angles)
for idx, angle in enumerate(angles):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, embeddings, paths, actual_issame, rotate_images, angle)
print('Angle: %1.3f Accuracy: %1.3f%c%1.3f' % (angle, np.mean(accuracy), u"\u00B1", 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()
result_dir = os.path.expanduser(FLAGS.model_dir)
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 True:
scales = np.arange(0.5, 1.5, 0.05)
scale_accuracy = [None] * len(scales)
for scale_idx, scale in enumerate(scales):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, embeddings, paths, actual_issame, scale_images, scale)
print('Scale: %1.3f Accuracy: %1.3f%c%1.3f' % (scale, np.mean(accuracy), u"\u00B1", 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()
result_dir = os.path.expanduser(FLAGS.model_dir)
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(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(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__))
store_training_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=(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,
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)
# Test on validation set
validate(sess, validation_set, epoch, images_placeholder,
phase_train_placeholder, global_step, embeddings,
loss, 'validation', summary_writer)
# Test on training set
validate(sess, train_set, epoch, images_placeholder,
phase_train_placeholder, global_step, embeddings,
loss, 'training', summary_writer)
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)
# Save the model if it hasn't been saved before
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():
# Creates graph from saved GraphDef
# NOTE: This does not work at the moment. Needs tensorflow to store variables in the graph_def.
#create_graph(os.path.join(FLAGS.model_dir, 'graphdef', 'graph_def.pb'))
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
mpl.interactive(True)
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, 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)
# Create a saver for restoring variable averages
ema = tf.train.ExponentialMovingAverage(1.0)
saver = tf.train.Saver(ema.variables_to_restore())
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=False))
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(os.path.expanduser(FLAGS.model_dir))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
# Run test on LFW to check accuracy for different horizontal/vertical translations of input images
if True:
offsets = np.arange(-30, 31, 3)
horizontal_offset_accuracy = [None] * len(offsets)
for idx, offset in enumerate(offsets):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, embeddings, paths, actual_issame, translate_images, (offset,0))
print('Hoffset: %1.3f Accuracy: %1.3f%c%1.3f' % (offset, np.mean(accuracy), u"\u00B1", 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, embeddings, paths, actual_issame, translate_images, (0,offset))
print('Voffset: %1.3f Accuracy: %1.3f%c%1.3f' % (offset, np.mean(accuracy), u"\u00B1", 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()
result_dir = os.path.expanduser(FLAGS.model_dir)
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'))
xxx = 1
# Run test on LFW to check accuracy for different rotation of input images
if True:
angles = np.arange(-30, 31, 3)
rotation_accuracy = [None] * len(angles)
for idx, angle in enumerate(angles):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, embeddings, paths, actual_issame, rotate_images, angle)
print('Angle: %1.3f Accuracy: %1.3f%c%1.3f' % (angle, np.mean(accuracy), u"\u00B1", 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()
result_dir = os.path.expanduser(FLAGS.model_dir)
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'))
xxx = 1
# Run test on LFW to check accuracy for different scaling of input images
if True:
scales = np.arange(0.5, 1.5, 0.05)
scale_accuracy = [None] * len(scales)
for scale_idx, scale in enumerate(scales):
accuracy = evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, embeddings, paths, actual_issame, scale_images, scale)
print('Scale: %1.3f Accuracy: %1.3f%c%1.3f' % (scale, np.mean(accuracy), u"\u00B1", 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()
result_dir = os.path.expanduser(FLAGS.model_dir)
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'))
xxx = 1
