def check_dataset(dataset):
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset')
paths, labels = facenet.get_image_paths_and_labels(dataset)
print(paths)
print(labels)
def process_data(self):
dataset = facenet.get_dataset(self.data_dir)
train_set, val_set = facenet.split_dataset(dataset, self.valid_ratio,
self.min_images_per_class,
self.mode)
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
val_image_list, val_label_list = facenet.get_image_paths_and_labels(
val_set)
image_list = self.preprocess_image(image_list)
val_image_list = self.preprocess_image(val_image_list)
train_data = zip(image_list, label_list)
val_data = zip(val_image_list, val_label_list)
train_rdd = self.sc.parallelize(train_data)
val_rdd = self.sc.parallelize(val_data)
train_df = train_rdd.toDF(DATAINDEX)
val_df = val_rdd.toDF(DATAINDEX)
return train_df, val_df
def train(self, dataset_folder, model_name):
dataset = facenet.get_dataset(dataset_folder)
# Check that there are at least one training image per class
# for cls in dataset:
# assert(len(cls.image_paths) > 0, 'There must be at least one image for each class in the dataset')
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
print("Calculating embeddings for new data")
data_emb = self.calculate_embeddings(paths, False)
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(model_name, 'wb') as outfile:
pickle.dump((data_emb, class_names, labels), outfile)
print('Saved classifier model to file "%s"' % model_name)
def fit(self):
self.model_status = 'TRAIN'
self.data_dir = My_align_dataset_mtcnn(0, 160, 32, True,
0.25).output_dir
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=self.seed)
if self.use_split_dataset:
dataset_tmp = facenet.get_dataset(self.data_dir)
train_set, test_set = self.split_dataset(
dataset_tmp, self.min_nrof_images_per_class,
self.nrof_train_images_per_class)
if (self.model_status == 'TRAIN'):
dataset = train_set
elif (self.model_status == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(self.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
self.paths, self.labels = facenet.get_image_paths_and_labels(
dataset)
print("paths", self.paths)
print("labels", self.labels)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(self.paths))
# Load the model
print('Loading feature extraction model', self.model)
load_model_YesOrNo = facenet.load_model(self.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(self.paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / self.batch_size))
print(nrof_images, self.batch_size, nrof_batches_per_epoch,
embedding_size)
self.emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * self.batch_size
end_index = min((i + 1) * self.batch_size, nrof_images)
paths_batch = self.paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
self.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
self.emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
print("shape", self.emb_array.shape)
self.classifier_filename_exp = os.path.expanduser(
self.classifier_filename)
# Train classifier
print('Training classifier')
self.classify_model = SVC(kernel='linear', probability=True)
self.classify_model.fit(self.emb_array, self.labels)
# Create a list of class names
self.class_names = [
cls.name.replace('_', ' ') for cls in dataset
]
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
fc.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__))
fc.store_revision_info(src_path, log_dir, " ".join(sys.argv))
np.random.seed(seed=args.seed)
random.seed(args.seed)
dataset = fc.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 = fc.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 = fc.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 = fc.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 = fc.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, _ = fc.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 = fc.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):
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=args.seed)
if args.use_split_dataset:
dataset_tmp = facenet.get_dataset(args.data_dir)
train_set, test_set = split_dataset(
dataset_tmp, args.min_nrof_images_per_class,
args.nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(args.data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
print('Number of classes: %d' % len(dataset))
print('Number of images: %d' % len(paths))
# Load the model
print('Loading feature extraction model')
facenet.load_model(args.model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / args.batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * args.batch_size
end_index = min((i + 1) * args.batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
args.image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(
args.classifier_filename)
if (args.mode == 'TRAIN'):
# Train classifier
print('Training classifier')
model = GaussianNB()
#model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
elif (args.mode == 'CLASSIFY'):
# Classify images
print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' %
classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s: %.3f' %
(i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
def classify(use_split_dataset, mode, data_dir, min_nrof_images_per_class,
nrof_train_images_per_class, model, classifier_filename,
batch_size, image_size):
seed = 666
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=seed)
if use_split_dataset:
dataset_tmp = facenet.get_dataset(data_dir)
train_set, test_set = split_dataset(
dataset_tmp, min_nrof_images_per_class,
nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
# print('Number of classes: %d' % len(dataset))
# print('Number of images: %d' % len(paths))
# Load the model
# print('Loading feature extraction model')
facenet.load_model(model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * batch_size
end_index = min((i + 1) * batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(classifier_filename)
res = []
# print('Testing classifier')
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
# print('Loaded classifier model from file "%s"' % classifier_filename_exp)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
for i in range(len(best_class_indices)):
print('%4d %s: %.3f' % (i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
res.append((i, class_names[best_class_indices[i]],
best_class_probabilities[i]))
accuracy = np.mean(np.equal(best_class_indices, labels))
print('Accuracy: %.3f' % accuracy)
return res
def train(use_split_dataset, mode, data_dir, min_nrof_images_per_class,
nrof_train_images_per_class, model, classifier_filename, batch_size,
image_size):
seed = 666
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=seed)
if use_split_dataset:
dataset_tmp = facenet.get_dataset(data_dir)
train_set, test_set = split_dataset(
dataset_tmp, min_nrof_images_per_class,
nrof_train_images_per_class)
if (args.mode == 'TRAIN'):
dataset = train_set
elif (args.mode == 'CLASSIFY'):
dataset = test_set
else:
dataset = facenet.get_dataset(data_dir)
# Check that there are at least one training image per class
for cls in dataset:
assert (
len(cls.image_paths) > 0,
'There must be at least one image for each class in the dataset'
)
paths, labels = facenet.get_image_paths_and_labels(dataset)
# print('Number of classes: %d' % len(dataset))
# print('Number of images: %d' % len(paths))
# Load the model
# print('Loading feature extraction model')
facenet.load_model(model)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embedding_size = embeddings.get_shape()[1]
# Run forward pass to calculate embeddings
print('Calculating features for images')
nrof_images = len(paths)
nrof_batches_per_epoch = int(
math.ceil(1.0 * nrof_images / batch_size))
emb_array = np.zeros((nrof_images, embedding_size))
for i in range(nrof_batches_per_epoch):
start_index = i * batch_size
end_index = min((i + 1) * batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False,
image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_array[start_index:end_index, :] = sess.run(
embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(classifier_filename)
print('Training classifier')
model = SVC(kernel='linear', probability=True)
model.fit(emb_array, labels)
# Create a list of class names
class_names = [cls.name.replace('_', ' ') for cls in dataset]
# Saving classifier model
with open(classifier_filename_exp, 'wb') as outfile:
pickle.dump((model, class_names), outfile)
print('Saved classifier model to file "%s"' %
classifier_filename_exp)
import sys
import math
import pickle
from sklearn.svm import SVC
from sklearn.cluster import KMeans
import pandas as pd
import cv2
import os
with tf.Graph().as_default():
with tf.Session() as sess:
np.random.seed(seed=666)
os.system("python facenet/src/align/align_dataset_mtcnn.py " +
sys.argv[1] +
" aligned --image_size 160 --margin 32 --random_order")
dataset = facenet.get_dataset("aligned")
paths, labels = facenet.get_image_paths_and_labels(dataset)
facenet.load_model('20180402-114759.pb')
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name(
"phase_train:0")
embedding_size = embeddings.get_shape()[1]
images = facenet.load_data(paths, False, False, 150)
emb_array_1 = np.zeros((len(labels), embedding_size))
j = min(len(images) - 1, 500)
i = 0
while j < len(images):
feed_dict = {
images_placeholder: images[i:j],
phase_train_placeholder: False
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)
# Removed lfw dir. Using custom dataset
# 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)
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)
facenet.load_model(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 embeding(model_dir='20170512-110547',
data_dir='database_aligned',
is_aligned=True,
image_size=160,
margin=44,
gpu_memory_fraction=1.0,
image_batch=1000,
embeddings_name='embeddings.npy',
labels_name='labels.npy',
labels_strings_name='label_strings.npy',
return_image_list=False):
train_set = facenet.get_dataset(data_dir)
image_list, label_list = facenet.get_image_paths_and_labels(train_set)
# fetch the classes (labels as strings) exactly as it's done in get_dataset
path_exp = os.path.expanduser(data_dir)
classes = [
path for path in os.listdir(path_exp)
if os.path.isdir(os.path.join(path_exp, path))
]
# get the label strings
label_strings = [
name for name in classes if os.path.isdir(os.path.join(path_exp, name))
]
with tf.Graph().as_default():
with tf.Session() as sess:
# Load model
facenet.load_model(model_dir)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0") # noqa: E501
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0") # noqa: E501
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# Run forward pass to calculate embeddings
nrof_images = len(image_list)
print('Number of images: ', nrof_images)
batch_size = image_batch
if nrof_images % batch_size == 0:
nrof_batches = nrof_images // batch_size
else:
nrof_batches = (nrof_images // batch_size) + 1
print('Number of batches: ', nrof_batches)
embedding_size = embeddings.get_shape()[1]
emb_array = np.zeros((nrof_images, embedding_size))
start_time = time.time()
for i in range(nrof_batches):
if i == nrof_batches - 1:
n = nrof_images
else:
n = i * batch_size + batch_size
# Get images for the batch
if is_aligned is True:
images = facenet.load_data(image_list[i * batch_size:n],
False, False, image_size)
else:
images = load_and_align_data(image_list[i * batch_size:n],
image_size, margin,
gpu_memory_fraction)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
# Use the facenet model to calculate embeddings
embed = sess.run(embeddings, feed_dict=feed_dict)
emb_array[i * batch_size:n, :] = embed
print('Completed batch', i + 1, 'of', nrof_batches)
run_time = time.time() - start_time
print('Run time: ', run_time)
# export embeddings and labels
label_list = np.array(label_list)
np.save(embeddings_name, emb_array)
if emb_array.size > 0:
labels_final = (label_list) - np.min(label_list)
np.save(labels_name, labels_final)
label_strings = np.array(label_strings)
np.save(labels_strings_name, label_strings[labels_final])
np.save('image_list.npy', image_list)
if return_image_list:
np.save('validation_image_list.npy', image_list)
return image_list, emb_array
def like_or_dislike_users(self, users):
# automatically like or dislike users based on your previously trained
# model on your historical preference.
# facenet settings from export_embeddings....
data_dir = 'temp_images_aligned'
embeddings_name = 'temp_embeddings.npy'
# labels_name = 'temp_labels.npy'
# labels_strings_name = 'temp_label_strings.npy'
is_aligned = True
image_size = 160
margin = 44
gpu_memory_fraction = 1.0
image_batch = 1000
prev_user = None
for user in users:
clean_temp_images()
urls = user.get_photos(width='640')
image_list = download_url_photos(urls, user.id, is_temp=True)
# align the database
tindetheus_align.main(input_dir='temp_images',
output_dir='temp_images_aligned')
# export the embeddings from the aligned database
train_set = facenet.get_dataset(data_dir)
image_list_temp, label_list = facenet.get_image_paths_and_labels(
train_set) # noqa: E501
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0") # noqa: E501
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0") # noqa: E501
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0") # noqa: E501
# Run forward pass to calculate embeddings
nrof_images = len(image_list_temp)
print('Number of images: ', nrof_images)
batch_size = image_batch
if nrof_images % batch_size == 0:
nrof_batches = nrof_images // batch_size
else:
nrof_batches = (nrof_images // batch_size) + 1
print('Number of batches: ', nrof_batches)
embedding_size = embeddings.get_shape()[1]
emb_array = np.zeros((nrof_images, embedding_size))
start_time = time.time()
for i in range(nrof_batches):
if i == nrof_batches - 1:
n = nrof_images
else:
n = i * batch_size + batch_size
# Get images for the batch
if is_aligned is True:
images = facenet.load_data(
image_list_temp[i * batch_size:n], # noqa: E501
False,
False,
image_size)
else:
images = load_and_align_data(
image_list_temp[i * batch_size:n], # noqa: E501
image_size,
margin,
gpu_memory_fraction)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
# Use the facenet model to calculate embeddings
embed = self.sess.run(embeddings, feed_dict=feed_dict)
emb_array[i * batch_size:n, :] = embed
print('Completed batch', i + 1, 'of', nrof_batches)
run_time = time.time() - start_time
print('Run time: ', run_time)
# export embeddings and labels
label_list = np.array(label_list)
np.save(embeddings_name, emb_array)
if emb_array.size > 0:
# calculate the n average embedding per profiles
X = calc_avg_emb_temp(emb_array)
# evaluate on the model
yhat = self.model.predict(X)
if yhat[0] == 1:
didILike = 'Like'
# check to see if this is the same user as before
if prev_user == user.id:
clean_temp_images_aligned()
print('\n\n You have already liked this user!!! \n \n')
print('This typically means you have used all of your'
' free likes. Exiting program!!! \n\n')
self.likes_left = -1
return
else:
prev_user = user.id
else:
didILike = 'Dislike'
else:
# there were no faces in this profile
didILike = 'Dislike'
print('**************************************************')
print(user.name, user.age, didILike)
print('**************************************************')
dbase_names = move_images_temp(image_list, user.id)
if didILike == 'Like':
print(user.like())
self.likes_left -= 1
else:
print(user.dislike())
userList = [
user.id, user.name, user.age, user.bio, user.distance_km,
user.jobs, user.schools,
user.get_photos(width='640'), dbase_names, didILike
]
self.al_database.append(userList)
np.save('al_database.npy', self.al_database)
clean_temp_images_aligned()
