hd.close()
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
# Norm for the prelogits
eps = 1e-5
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)
# inference_loss, logit = cos_loss(prelogits, labels, args.class_number)
w_init_method = slim.initializers.xavier_initializer()
inference_loss, logit = arcface_loss(embedding=embeddings,
labels=labels,
w_init=w_init_method,
out_num=args.class_number)
tf.add_to_collection('losses', inference_loss)
# total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([inference_loss] + regularization_losses,
name='total_loss')
# define the learning rate schedule
learning_rate = tf.train.piecewise_constant(
epoch,
boundaries=args.lr_schedule,
values=[0.1, 0.01, 0.001, 0.0001, 0.00001],
name='lr_schedule')
db, args.image_size,
args) #預設是lfw,image size 27行 112*112，得到dataset BGR [112, 112, 3]
ver_list.append(data_set) #把驗證集加到ver_list裡
ver_name_list.append(db) #把驗證集path加到ver_name_list裡
# 3. define network, loss, optimize method, learning rate schedule, summary writer, saver
# 3.1 inference phase
w_init_method = tf.contrib.layers.xavier_initializer(uniform=False)
net = get_resnet(images,
args.net_depth,
type='ir',
w_init=w_init_method,
trainable=True,
keep_rate=dropout_rate)
# 3.2 get arcface loss
logit = arcface_loss(embedding=net.outputs,
labels=labels,
w_init=w_init_method,
out_num=args.num_output)
# test net because of batch normal layer
tl.layers.set_name_reuse(True)
test_net = get_resnet(images,
args.net_depth,
type='ir',
w_init=w_init_method,
trainable=False,
reuse=True,
keep_rate=dropout_rate)
embedding_tensor = test_net.outputs
# 3.3 define the cross entropy
inference_loss = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logit,
labels=labels))
def custom_insightface_evaluation(args):
tf.reset_default_graph()
# Read the directory containing images
pairs = read_pairs(args.insightface_pair)
image_list, issame_list = get_paths_with_pairs(
args.insightface_dataset_dir, pairs)
# Evaluate custom dataset with facenet pre-trained model
print("Getting embeddings with facenet pre-trained model")
# Getting batched images by TF dataset
tf_dataset = facenet.tf_gen_dataset(
image_list=image_list,
label_list=None,
nrof_preprocess_threads=args.nrof_preprocess_threads,
image_size=args.insightface_dataset_dir,
method='cache_slices',
BATCH_SIZE=args.batch_size,
repeat_count=1,
to_float32=True,
shuffle=False)
# tf_dataset = facenet.tf_gen_dataset(image_list, label_list, args.nrof_preprocess_threads, args.facenet_image_size, method='cache_slices',
# BATCH_SIZE=args.batch_size, repeat_count=1, shuffle=False)
tf_dataset_iterator = tf_dataset.make_initializable_iterator()
tf_dataset_next_element = tf_dataset_iterator.get_next()
images = tf.placeholder(name='img_inputs',
shape=[
None, args.insightface_image_size,
args.insightface_image_size, 3
],
dtype=tf.float32)
labels = tf.placeholder(name='img_labels', shape=[
None,
], dtype=tf.int64)
dropout_rate = tf.placeholder(name='dropout_rate', dtype=tf.float32)
w_init_method = tf.contrib.layers.xavier_initializer(uniform=False)
net = L_Resnet_E_IR_fix_issue9.get_resnet(images,
args.net_depth,
type='ir',
w_init=w_init_method,
trainable=False,
keep_rate=dropout_rate)
embeddings = net.outputs
# mv_mean = tl.layers.get_variables_with_name('resnet_v1_50/bn0/moving_mean', False, True)[0]
# 3.2 get arcface loss
logit = arcface_loss(embedding=net.outputs,
labels=labels,
w_init=w_init_method,
out_num=args.num_output)
sess = tf.Session()
saver = tf.train.Saver()
feed_dict = {}
feed_dict_flip = {}
path = args.ckpt_file + args.ckpt_index_list[0]
saver.restore(sess, path)
print('ckpt file %s restored!' % args.ckpt_index_list[0])
feed_dict.update(tl.utils.dict_to_one(net.all_drop))
feed_dict_flip.update(tl.utils.dict_to_one(net.all_drop))
feed_dict[dropout_rate] = 1.0
feed_dict_flip[dropout_rate] = 1.0
batch_size = args.batch_size
input_placeholder = images
sess.run(tf_dataset_iterator.initializer)
print('getting embeddings..')
total_time = 0
batch_number = 0
embeddings_array = None
embeddings_array_flip = None
while True:
try:
images = sess.run(tf_dataset_next_element)
data_tmp = images.copy() # fix issues #4
for i in range(data_tmp.shape[0]):
data_tmp[i, ...] -= 127.5
data_tmp[i, ...] *= 0.0078125
data_tmp[i, ...] = cv2.cvtColor(data_tmp[i, ...],
cv2.COLOR_RGB2BGR)
# Getting flip to left_right batched images by TF dataset
data_tmp_flip = images.copy() # fix issues #4
for i in range(data_tmp_flip.shape[0]):
data_tmp_flip[i, ...] = np.fliplr(data_tmp_flip[i, ...])
data_tmp_flip[i, ...] -= 127.5
data_tmp_flip[i, ...] *= 0.0078125
data_tmp_flip[i, ...] = cv2.cvtColor(data_tmp_flip[i, ...],
cv2.COLOR_RGB2BGR)
start_time = time.time()
feed_dict[input_placeholder] = data_tmp
_embeddings = sess.run(embeddings, feed_dict)
feed_dict_flip[input_placeholder] = data_tmp_flip
_embeddings_flip = sess.run(embeddings, feed_dict_flip)
if embeddings_array is None:
embeddings_array = np.zeros(
(len(image_list), _embeddings.shape[1]))
embeddings_array_flip = np.zeros(
(len(image_list), _embeddings_flip.shape[1]))
try:
embeddings_array[batch_number *
batch_size:min((batch_number + 1) *
batch_size, len(image_list)),
...] = _embeddings
embeddings_array_flip[batch_number * batch_size:min(
(batch_number + 1) * batch_size, len(image_list)),
...] = _embeddings_flip
# print('try: ', batch_number * batch_size, min((batch_number + 1) * batch_size, len(image_list)), ...)
except ValueError:
print(
'batch_number*batch_size value is %d min((batch_number+1)*batch_size, len(image_list)) %d,'
' batch_size %d, data.shape[0] %d' %
(batch_number * batch_size,
min((batch_number + 1) * batch_size,
len(image_list)), batch_size, images.shape[0]))
print('except: ', batch_number * batch_size,
min((batch_number + 1) * batch_size, images.shape[0]),
...)
duration = time.time() - start_time
batch_number += 1
total_time += duration
except tf.errors.OutOfRangeError:
print(
'tf.errors.OutOfRangeError, Reinitialize tf_dataset_iterator')
sess.run(tf_dataset_iterator.initializer)
break
print(f"total_time: {total_time}")
_xnorm = 0.0
_xnorm_cnt = 0
for embed in [embeddings_array, embeddings_array_flip]:
for i in range(embed.shape[0]):
_em = embed[i]
_norm = np.linalg.norm(_em)
# print(_em.shape, _norm)
_xnorm += _norm
_xnorm_cnt += 1
_xnorm /= _xnorm_cnt
final_embeddings_output = embeddings_array + embeddings_array_flip
final_embeddings_output = sklearn.preprocessing.normalize(
final_embeddings_output)
print(final_embeddings_output.shape)
tpr, fpr, accuracy, val, val_std, far = verification.evaluate(
final_embeddings_output, issame_list, nrof_folds=10)
acc2, std2 = np.mean(accuracy), np.std(accuracy)
auc = metrics.auc(fpr, tpr)
print('XNorm: %f' % (_xnorm))
print('Accuracy-Flip: %1.5f+-%1.5f' % (acc2, std2))
print('TPR: ', np.mean(tpr), 'FPR: ', np.mean(fpr))
print('Area Under Curve (AUC): %1.3f' % auc)
tpr_lfw, fpr_lfw, accuracy_lfw, val_lfw, val_std_lfw, far_lfw = lfw.evaluate(
final_embeddings_output,
issame_list,
nrof_folds=10,
distance_metric=0,
subtract_mean=False)
print('accuracy_lfw: %2.5f+-%2.5f' %
(np.mean(accuracy_lfw), np.std(accuracy_lfw)))
print(
f"val_lfw: {val_lfw}, val_std_lfw: {val_std_lfw}, far_lfw: {far_lfw}")
print('val_lfw rate: %2.5f+-%2.5f @ FAR=%2.5f' %
(val_lfw, val_std_lfw, far_lfw))
auc_lfw = metrics.auc(fpr_lfw, tpr_lfw)
print('TPR_LFW:', np.mean(tpr_lfw), 'FPR_LFW: ', np.mean(fpr_lfw))
print('Area Under Curve LFW (AUC): %1.3f' % auc_lfw)
sess.close()
return acc2, std2, _xnorm, [embeddings_array, embeddings_array_flip]
loss_keys = []
with tf.variable_scope(tf.get_variable_scope()):
for i in range(args.num_gpus):
with tf.device('/gpu:%d' % i):
with tf.name_scope('%s_%d' % (args.tower_name, i)) as scope:
# net = get_resnet(images_s[i], args.net_depth, type='ir', w_init=w_init_method, trainable=True, keep_rate=dropout_rate)
prelogits, net_points = inference(images_s[i], bottleneck_layer_size=512,
phase_train=True, weight_decay=args.weight_decay)
embeddings = tf.nn.l2_normalize(prelogits, 1, 1e-10, name='embeddings')
eps = 1e-5
prelogits_norm = tf.reduce_mean(tf.norm(tf.abs(prelogits) + eps, ord=1.0, axis=1))
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES, prelogits_norm * 2e-5)
w_init_method = slim.initializers.xavier_initializer()
logit = arcface_loss(embedding=embeddings, labels=labels_s[i], w_init=w_init_method, out_num=args.num_output)
# Reuse variables for the next tower.
tf.get_variable_scope().reuse_variables()
# define the cross entropy
inference_loss = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logit, labels=labels_s[i]))
tf.add_to_collection('losses', inference_loss)
regularization_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
reg_loss = tf.add_n(regularization_losses,name='reg_loss')
total_loss = tf.add_n([inference_loss] + regularization_losses, name='total_loss')
# define weight deacy losses
loss_dict[('inference_loss_%s_%d' % ('gpu', i))] = inference_loss
],
dtype=tf.int64)
t_model_path = args.teacher_model_path
w_init_method = tf.contrib.layers.xavier_initializer(uniform=False)
net_t = get_resnet(images_t,
args.net_depth,
type='ir',
w_init=w_init_method,
trainable=False,
keep_rate=dropout_keep_rate)
embedding_tensor_t = net_t.outputs
logit_t = arcface_loss(embedding=embedding_tensor_t,
labels=labels_t,
var_scope='arcface_loss',
w_init=w_init_method,
out_num=args.num_output)
t_tau = tf.scalar_mul(1.0 / args.tau, logit_t)
pred_t = tf.nn.softmax(logit_t)
acc_t = tf.reduce_mean(
tf.cast(tf.equal(tf.argmax(pred_t, axis=1), labels_t),
dtype=tf.float32))
print('########################')
print('teacher model start to restore')
saver_restore_t = tf.train.Saver()
config = tf.ConfigProto(allow_soft_placement=True,
log_device_placement=args.log_device_mapping)
config.gpu_options.allow_growth = True
sess_t = tf.Session(config=config)
def get_insightface_embeddings(args):
tf.reset_default_graph()
# Read the directory containing images
dataset = facenet.get_dataset(args.insightface_dataset_dir)
nrof_classes = len(dataset)
# Evaluate custom dataset with facenet pre-trained model
print("Getting embeddings with facenet pre-trained model")
# Get a list of image paths and their labels
image_list, label_list = facenet.get_image_paths_and_labels(dataset)
assert len(image_list) > 0, 'The dataset should not be empty'
print('Number of classes in dataset: %d' % nrof_classes)
print('Number of examples in dataset: %d' % len(image_list))
# Getting batched images by TF dataset
tf_dataset = facenet.tf_gen_dataset(
image_list=image_list,
label_list=None,
nrof_preprocess_threads=args.nrof_preprocess_threads,
image_size=args.insightface_dataset_dir,
method='cache_slices',
BATCH_SIZE=args.batch_size,
repeat_count=1,
to_float32=True,
shuffle=False)
tf_dataset_iterator = tf_dataset.make_initializable_iterator()
tf_dataset_next_element = tf_dataset_iterator.get_next()
images = tf.placeholder(name='img_inputs',
shape=[
None, args.insightface_image_size,
args.insightface_image_size, 3
],
dtype=tf.float32)
labels = tf.placeholder(name='img_labels', shape=[
None,
], dtype=tf.int64)
dropout_rate = tf.placeholder(name='dropout_rate', dtype=tf.float32)
w_init_method = tf.contrib.layers.xavier_initializer(uniform=False)
net = L_Resnet_E_IR_fix_issue9.get_resnet(images,
args.net_depth,
type='ir',
w_init=w_init_method,
trainable=False,
keep_rate=dropout_rate)
embeddings = net.outputs
# mv_mean = tl.layers.get_variables_with_name('resnet_v1_50/bn0/moving_mean', False, True)[0]
# 3.2 get arcface loss
logit = arcface_loss(embedding=net.outputs,
labels=labels,
w_init=w_init_method,
out_num=args.num_output)
sess = tf.Session()
saver = tf.train.Saver()
feed_dict = {}
feed_dict_flip = {}
path = args.ckpt_file + args.ckpt_index_list[0]
saver.restore(sess, path)
print('ckpt file %s restored!' % args.ckpt_index_list[0])
feed_dict.update(tl.utils.dict_to_one(net.all_drop))
feed_dict_flip.update(tl.utils.dict_to_one(net.all_drop))
feed_dict[dropout_rate] = 1.0
feed_dict_flip[dropout_rate] = 1.0
batch_size = args.batch_size
input_placeholder = images
sess.run(tf_dataset_iterator.initializer)
# sess.run(tf_dataset_iterator_flip.initializer)
print('getting embeddings..')
total_time = 0
batch_number = 0
embeddings_array = None
embeddings_array_flip = None
while True:
try:
images = sess.run(tf_dataset_next_element)
data_tmp = images.copy() # fix issues #4
for i in range(data_tmp.shape[0]):
data_tmp[i, ...] -= 127.5
data_tmp[i, ...] *= 0.0078125
data_tmp[i, ...] = cv2.cvtColor(data_tmp[i, ...],
cv2.COLOR_RGB2BGR)
# Getting flip to left_right batched images by TF dataset
data_tmp_flip = images.copy() # fix issues #4
for i in range(data_tmp_flip.shape[0]):
data_tmp_flip[i, ...] = np.fliplr(data_tmp_flip[i, ...])
data_tmp_flip[i, ...] -= 127.5
data_tmp_flip[i, ...] *= 0.0078125
data_tmp_flip[i, ...] = cv2.cvtColor(data_tmp_flip[i, ...],
cv2.COLOR_RGB2BGR)
start_time = time.time()
feed_dict[input_placeholder] = data_tmp
_embeddings = sess.run(embeddings, feed_dict)
feed_dict_flip[input_placeholder] = data_tmp_flip
_embeddings_flip = sess.run(embeddings, feed_dict_flip)
if embeddings_array is None:
embeddings_array = np.zeros(
(len(image_list), _embeddings.shape[1]))
embeddings_array_flip = np.zeros(
(len(image_list), _embeddings_flip.shape[1]))
try:
embeddings_array[batch_number *
batch_size:min((batch_number + 1) *
batch_size, len(image_list)),
...] = _embeddings
embeddings_array_flip[batch_number * batch_size:min(
(batch_number + 1) * batch_size, len(image_list)),
...] = _embeddings_flip
# print('try: ', batch_number * batch_size, min((batch_number + 1) * batch_size, len(image_list)), ...)
except ValueError:
print(
'batch_number*batch_size value is %d min((batch_number+1)*batch_size, len(image_list)) %d,'
' batch_size %d, data.shape[0] %d' %
(batch_number * batch_size,
min((batch_number + 1) * batch_size,
len(image_list)), batch_size, images.shape[0]))
print('except: ', batch_number * batch_size,
min((batch_number + 1) * batch_size, images.shape[0]),
...)
duration = time.time() - start_time
batch_number += 1
total_time += duration
except tf.errors.OutOfRangeError:
print(
'tf.errors.OutOfRangeError, Reinitialize tf_dataset_iterator')
sess.run(tf_dataset_iterator.initializer)
break
print(f"total_time: {total_time}")
_xnorm = 0.0
_xnorm_cnt = 0
for embed in [embeddings_array, embeddings_array_flip]:
for i in range(embed.shape[0]):
_em = embed[i]
_norm = np.linalg.norm(_em)
# print(_em.shape, _norm)
_xnorm += _norm
_xnorm_cnt += 1
_xnorm /= _xnorm_cnt
final_embeddings_output = embeddings_array + embeddings_array_flip
final_embeddings_output = sklearn.preprocessing.normalize(
final_embeddings_output)
print(final_embeddings_output.shape)
sess.close()
return embeddings_array, embeddings_array_flip, final_embeddings_output, _xnorm
name='lr_schedule')
# 3.3 define the optimize method
opt = tf.train.MomentumOptimizer(learning_rate=lr, momentum=args.momentum)
# Calculate the gradients for each model tower.
tower_grads = []
tl.layers.set_name_reuse(True)
loss_dict = {}
drop_dict = {}
loss_keys = []
with tf.variable_scope(tf.get_variable_scope()):
for i in range(args.num_gpus):
with tf.device('/gpu:%d' % i):
with tf.name_scope('%s_%d' % (args.tower_name, i)) as scope:
net = get_resnet(images_s[i], args.net_depth, type='ir', w_init=w_init_method, trainable=True, keep_rate=dropout_rate)
logit = arcface_loss(embedding=net.outputs, labels=labels_s[i], w_init=w_init_method, out_num=args.num_output)
# Reuse variables for the next tower.
tf.get_variable_scope().reuse_variables()
# define the cross entropy
inference_loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logit, labels=labels_s[i]))
# define weight deacy losses
wd_loss = 0
for weights in tl.layers.get_variables_with_name('W_conv2d', True, True):
wd_loss += tf.contrib.layers.l2_regularizer(args.weight_deacy)(weights)
for W in tl.layers.get_variables_with_name('resnet_v1_50/E_DenseLayer/W', True, True):
wd_loss += tf.contrib.layers.l2_regularizer(args.weight_deacy)(W)
for weights in tl.layers.get_variables_with_name('embedding_weights', True, True):
wd_loss += tf.contrib.layers.l2_regularizer(args.weight_deacy)(weights)
for gamma in tl.layers.get_variables_with_name('gamma', True, True):
wd_loss += tf.contrib.layers.l2_regularizer(args.weight_deacy)(gamma)
for alphas in tl.layers.get_variables_with_name('alphas', True, True):
w_init_method = tf.contrib.layers.xavier_initializer(
uniform=False) # 随机初始化权重先把空架子搭起来，后续再往里面restore train好的权重
net = get_resnet(
images,
args.net_depth,
type='ir',
w_init=w_init_method,
trainable=False,
keep_rate=dropout_rate) # L_Resnet_E_IR (?, 112,112,3)>(?, 512)
embedding_tensor = net.outputs
# mv_mean = tl.layers.get_variables_with_name('resnet_v1_50/bn0/moving_mean', False, True)[0]
# 3.2 get arcface loss
logit = arcface_loss(
embedding=net.outputs,
labels=labels,
w_init=w_init_method,
out_num=args.num_output) # (?, 512)，(?,)，initializer ，85164
gpu_config = tf.ConfigProto()
gpu_config.gpu_options.allow_growth = True
sess = tf.Session(config=gpu_config)
saver = tf.train.Saver()
result_index = []
for file_index in args.ckpt_index_list:
feed_dict_test = {}
path = args.ckpt_file + file_index
saver.restore(sess, path)
print('ckpt file %s restored!' % file_index)
feed_dict_test.update(tl.utils.dict_to_one(net.all_drop))
exclusions = None
if checkpoint_exclude_scopes:
exclusions = [
scope.strip() for scope in checkpoint_exclude_scopes.split(',')]
variables_to_restore = []
for var in slim.get_model_variables():
excluded = False
for exclusion in exclusions:
if var.op.name.startswith(exclusion):
excluded = True
if not excluded:
variables_to_restore.append(var)
print('################################')
print('variables in ori model to restore are set')
logit = arcface_loss(embedding=net, labels=labels, var_scope='arcface_loss', w_init=w_init_method, out_num=args.num_output)
# test net because of batch normal layera
# tl.layers.set_name_reuse(True)
# test_net = get_resnet(images, args.net_depth, type='ir', w_init=w_init_method, trainable=False, reuse=True, keep_rate=dropout_rate)
# embedding_tensor = test_net.outputs
# 3.3 define the cross entropy
inference_loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logit, labels=labels))
# inference_loss_avg = tf.reduce_mean(inference_loss)
# 3.4 define weight deacy losses
# for var in tf.trainable_variables():
# print(var.name)
# print('##########'*30)
# wd_loss = tf.convert_to_tensor(np.array([0.,], dtype=np.float32))
# 3.5 total losses
# total_loss = inference_loss + wd_loss
# Norm for the prelogits
prelogits_norm = tf.reduce_mean(
tf.norm(tf.abs(prelogits) + 1e-5,
ord=args.prelogits_norm_p,
axis=1))
tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES,
prelogits_norm * args.prelogits_norm_loss_factor)
if args.loss_type == 'softmax':
inference_loss, logit = softmax_loss(prelogits, labels,
args.num_output)
elif args.loss_type == 'arcface':
inference_loss, logit = arcface_loss(
embeddings,
labels,
args.num_output,
w_init=slim.initializers.xavier_initializer())
else:
print('loss_type is invalid, you can use softmax or arcface.')
exit(0)
# total losses
regularization_losses = tf.get_collection(
tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n([inference_loss] + regularization_losses,
name='total_loss')
# define the learning rate schedule
learning_rate = tf.train.piecewise_constant(
global_step,
drop_dict = {}
loss_keys = []
with tf.variable_scope(tf.get_variable_scope()):
for iter_gpus in num_gpus:
with tf.device('/gpu:%d' % iter_gpus):
with tf.name_scope('%s_%d' % (tower_name, iter_gpus)) as scope:
net = get_resnet(images_s[iter_gpus],
net_depth,
type=is_seblock,
w_init=w_init_method,
trainable=True,
keep_rate=dropout_rate)
if is_arcloss == 1:
logit = arcface_loss(embedding=net.outputs,
labels=labels[iter_gpus],
w_init=w_init_method,
out_num=num_output,
s=loss_s,
m=loss_m)
else:
logit = cosineface_losses(embedding=net.outputs,
labels=labels_s[iter_gpus],
w_init=w_init_method,
out_num=num_output,
s=loss_s,
m=loss_m)
# Reuse variables for the next tower.
tf.get_variable_scope().reuse_variables(
) # 同名变量将会复用，假设现在gpu0上创建了两个变量var0，var1，那么在gpu1上创建计算图的时候，如果还有var0和var1，则默认复用之前gpu0上的创建的那两个值
# define the cross entropy
inference_loss = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(
