def 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, loss, train_op, summary_op,
summary_writer, regularization_losses, learning_rate_schedule_file):
batch_number = 0
if args.learning_rate > 0.0:
lr = args.learning_rate
else:
lr = facenet.get_learning_rate_from_file(learning_rate_schedule_file,
epoch)
index_epoch = sess.run(index_dequeue_op)
label_epoch = np.array(label_list)[index_epoch]
image_epoch = np.array(image_list)[index_epoch]
# Enqueue one epoch of image paths and labels
labels_array = np.expand_dims(np.array(label_epoch), 1)
image_paths_array = np.expand_dims(np.array(image_epoch), 1)
sess.run(
enqueue_op, {
image_paths_placeholder: image_paths_array,
labels_placeholder: labels_array
})
# Training loop
train_time = 0
while batch_number < args.epoch_size:
start_time = time.time()
feed_dict = {
learning_rate_placeholder: lr,
phase_train_placeholder: True,
batch_size_placeholder: args.batch_size
}
if (batch_number % 100 == 0):
err, _, step, reg_loss, summary_str = sess.run([
loss, train_op, global_step, regularization_losses, summary_op
],
feed_dict=feed_dict)
summary_writer.add_summary(summary_str, global_step=step)
else:
err, _, step, reg_loss = sess.run(
[loss, train_op, global_step, regularization_losses],
feed_dict=feed_dict)
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\tLoss %2.3f\tRegLoss %2.3f' %
(epoch, batch_number + 1, args.epoch_size, duration, err,
np.sum(reg_loss)))
batch_number += 1
train_time += duration
# Add validation loss and accuracy to summary
summary = tf.Summary()
#pylint: disable=maybe-no-member
summary.value.add(tag='time/total', simple_value=train_time)
summary_writer.add_summary(summary, step)
return step
def train(args, sess, src_dataset, tgt_dataset, epoch, image_paths_placeholder,
labels_placeholder, labels_batch, batch_size_placeholder,
learning_rate_placeholder, phase_train_placeholder, enqueue_op,
input_queue, global_step, embeddings, total_loss, triplet_loss,
adv_loss, reg_loss, train_op, summary_writer,
learning_rate_schedule_file, embedding_size):
batch_number = 0
if args.learning_rate > 0.0:
lr = args.learning_rate
else:
lr = facenet.get_learning_rate_from_file(learning_rate_schedule_file,
epoch)
while batch_number < args.epoch_size:
# Sample people randomly from the dataset
src_image_paths, src_num_per_class = sample_people(
src_dataset, args.people_per_batch, args.images_per_person)
tgt_image_paths, tgt_num_per_class = sample_people(
tgt_dataset,
args.people_per_batch,
args.images_per_person,
nb_images=len(src_image_paths) / 3)
print('Running forward pass on sampled images: ', end='')
start_time = time.time()
src_image_paths_array = np.reshape(
np.expand_dims(np.array(src_image_paths), 1), (-1, 3))
tgt_image_paths_array = np.expand_dims(np.array(tgt_image_paths),
axis=0).T
image_paths_array = np.concatenate(
(src_image_paths_array, tgt_image_paths_array), axis=1)
nrof_examples = image_paths_array.size
labels_array = np.reshape(np.arange(nrof_examples), (-1, 4))
sess.run(
enqueue_op, {
image_paths_placeholder: image_paths_array,
labels_placeholder: labels_array
})
emb_array = np.zeros((nrof_examples, embedding_size))
nrof_batches = int(np.ceil(nrof_examples / args.batch_size))
for i in range(nrof_batches):
batch_size = min(nrof_examples - i * args.batch_size,
args.batch_size)
emb, lab = sess.run(
[embeddings, labels_batch],
feed_dict={
batch_size_placeholder: batch_size,
learning_rate_placeholder: lr,
phase_train_placeholder: True
})
emb_array[lab, :] = emb
emb_array = np.lib.stride_tricks.as_strided(
emb_array, (nrof_examples // 4, 4, embedding_size))
src_emb_array = np.reshape(emb_array[:, 0:3], (-1, embedding_size))
tgt_emb_array = emb_array[:, 3]
print('%.3f' % (time.time() - start_time))
# Select triplets based on the embeddings
print('Selecting suitable triplets for training')
quadruplets, nrof_random_negs, nrof_quadruplets = adversarialloss.select_quadruplets(
src_emb_array, tgt_emb_array, src_num_per_class, src_image_paths,
tgt_image_paths, args.people_per_batch, args.alpha)
selection_time = time.time() - start_time
print(
'(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' %
(nrof_random_negs, nrof_quadruplets, selection_time))
# Perform training on the selected quadruplets
nrof_batches = int(np.ceil(nrof_quadruplets * 4 / args.batch_size))
quadruplets_paths = list(itertools.chain(*quadruplets))
labels_array = np.reshape(np.arange(len(quadruplets_paths)), (-1, 4))
quadruplets_paths_array = np.reshape(
np.expand_dims(np.array(quadruplets_paths), 1), (-1, 4))
sess.run(
enqueue_op, {
image_paths_placeholder: quadruplets_paths_array,
labels_placeholder: labels_array
})
nrof_examples = len(quadruplets_paths)
train_time = 0
i = 0
emb_array = np.zeros((nrof_examples, embedding_size))
loss_array = np.zeros((nrof_quadruplets, ))
summary = tf.Summary()
step = 0
while i < nrof_batches:
start_time = time.time()
batch_size = min(nrof_examples - i * args.batch_size,
args.batch_size)
feed_dict = {
batch_size_placeholder: batch_size,
learning_rate_placeholder: lr,
phase_train_placeholder: True
}
triplet_err, adv_err, total_err, _, step, emb, lab = sess.run(
[
triplet_loss, adv_loss, total_loss, train_op, global_step,
embeddings, labels_batch
],
feed_dict=feed_dict)
#emb_array[lab,:] = emb
#loss_array[i] = err
duration = time.time() - start_time
print(
'Epoch: [%d][%d/%d]\tTime %.3f\nTotal loss %2.3f\nTriplet loss %2.3f\nAdv loss %2.3f'
% (epoch, batch_number + 1, args.epoch_size, duration,
total_err, triplet_err, adv_err))
batch_number += 1
i += 1
train_time += duration
summary.value.add(tag='loss/total_loss', simple_value=total_err)
summary.value.add(tag='loss/triplet_loss',
simple_value=triplet_err)
summary.value.add(tag='loss/adv_loss', simple_value=adv_err)
#summary.value.add(tag='loss/regularisationL2_err', simple_value=reg_err)
# Add validation loss and accuracy to summary
#pylint: disable=maybe-no-member
summary.value.add(tag='time/selection', simple_value=selection_time)
summary_writer.add_summary(summary, step)
return step
def 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, step, loss, train_op,
summary_op, summary_writer, reg_losses, learning_rate_schedule_file,
stat, cross_entropy_mean, accuracy, learning_rate, prelogits,
prelogits_center_loss, random_rotate, random_crop, random_flip,
prelogits_norm, prelogits_hist_max, use_fixed_image_standardization):
batch_number = 0
if args.learning_rate > 0.0:
lr = args.learning_rate
else:
lr = facenet.get_learning_rate_from_file(learning_rate_schedule_file,
epoch)
if lr <= 0:
return False
index_epoch = sess.run(index_dequeue_op)
label_epoch = np.array(label_list)[index_epoch]
image_epoch = np.array(image_list)[index_epoch]
# Enqueue one epoch of image paths and labels
labels_array = np.expand_dims(np.array(label_epoch), 1)
image_paths_array = np.expand_dims(np.array(image_epoch), 1)
control_value = facenet.RANDOM_ROTATE * random_rotate + facenet.RANDOM_CROP * random_crop + facenet.RANDOM_FLIP * random_flip + facenet.FIXED_STANDARDIZATION * use_fixed_image_standardization
control_array = np.ones_like(labels_array) * control_value
sess.run(
enqueue_op, {
image_paths_placeholder: image_paths_array,
labels_placeholder: labels_array,
control_placeholder: control_array
})
# Training loop
train_time = 0
while batch_number < args.epoch_size:
start_time = time.time()
feed_dict = {
learning_rate_placeholder: lr,
phase_train_placeholder: True,
batch_size_placeholder: args.batch_size
}
tensor_list = [
loss, train_op, step, reg_losses, prelogits, cross_entropy_mean,
learning_rate, prelogits_norm, accuracy, prelogits_center_loss
]
if batch_number % 100 == 0:
loss_, _, step_, reg_losses_, prelogits_, cross_entropy_mean_, lr_, prelogits_norm_, accuracy_, center_loss_, summary_str = sess.run(
tensor_list + [summary_op], feed_dict=feed_dict)
summary_writer.add_summary(summary_str, global_step=step_)
else:
loss_, _, step_, reg_losses_, prelogits_, cross_entropy_mean_, lr_, prelogits_norm_, accuracy_, center_loss_ = sess.run(
tensor_list, feed_dict=feed_dict)
duration = time.time() - start_time
stat['loss'][step_ - 1] = loss_
stat['center_loss'][step_ - 1] = center_loss_
stat['reg_loss'][step_ - 1] = np.sum(reg_losses_)
stat['xent_loss'][step_ - 1] = cross_entropy_mean_
stat['prelogits_norm'][step_ - 1] = prelogits_norm_
stat['learning_rate'][epoch - 1] = lr_
stat['accuracy'][step_ - 1] = accuracy_
stat['prelogits_hist'][epoch - 1, :] += \
np.histogram(np.minimum(np.abs(prelogits_), prelogits_hist_max), bins=1000, range=(0.0, prelogits_hist_max))[0]
duration = time.time() - start_time
print(
'Epoch: [%d][%d/%d]\tTime %.3f\tLoss %2.3f\tXent %2.3f\tRegLoss %2.3f\tAccuracy %2.3f\tLr %2.5f\tCl %2.3f'
% (epoch, batch_number + 1,
args.epoch_size, duration, loss_, cross_entropy_mean_,
np.sum(reg_losses_), accuracy_, lr_, center_loss_))
batch_number += 1
train_time += duration
# Add validation loss and accuracy to summary
summary = tf.Summary()
# pylint: disable=maybe-no-member
summary.value.add(tag='time/total', simple_value=train_time)
summary_writer.add_summary(summary, global_step=step_)
return True
def train(args, sess, dataset, epoch, image_paths_placeholder,
labels_placeholder, labels_batch, batch_size_placeholder,
learning_rate_placeholder, phase_train_placeholder, enqueue_op,
input_queue, global_step, embeddings, loss, train_op, summary_writer,
learning_rate_schedule_file, embedding_size):
batch_number = 0
if args.learning_rate > 0.0:
lr = args.learning_rate
else:
lr = facenet.get_learning_rate_from_file(learning_rate_schedule_file,
epoch)
while batch_number < args.epoch_size:
# Sample people randomly from the dataset
video_paths, still_paths, num_per_class = sample_people(
dataset, args.people_per_batch, args.images_per_person)
# Video samples forward pass
print('Running forward pass on video sampled images: ', end='')
start_time = time.time()
nrof_examples = args.people_per_batch * args.images_per_person
labels_array = np.reshape(np.arange(nrof_examples), (-1, 3))
image_paths_array = np.reshape(
np.expand_dims(np.array(video_paths), 1), (-1, 3))
sess.run(
enqueue_op, {
image_paths_placeholder: image_paths_array,
labels_placeholder: labels_array
})
video_emb_array = np.zeros((nrof_examples, embedding_size))
nrof_batches = int(np.ceil(nrof_examples / args.batch_size))
for i in range(nrof_batches):
batch_size = min(nrof_examples - i * args.batch_size,
args.batch_size)
video_emb, lab = sess.run(
[embeddings, labels_batch],
feed_dict={
batch_size_placeholder: batch_size,
learning_rate_placeholder: lr,
phase_train_placeholder: True
})
video_emb_array[lab, :] = video_emb
print('%.3f' % (time.time() - start_time))
# Still samples forward pass
print('Running forward pass on still sampled images: ', end='')
start_time = time.time()
nrof_examples = args.people_per_batch # * args.images_per_person
labels_array = np.reshape(np.arange(nrof_examples), (-1, 3))
still_paths_array = np.reshape(
np.expand_dims(np.array(still_paths), 1), (-1, 3))
sess.run(
enqueue_op, {
image_paths_placeholder: still_paths_array,
labels_placeholder: labels_array
})
still_emb_array = np.zeros((nrof_examples, embedding_size))
nrof_batches = int(np.ceil(nrof_examples / args.batch_size))
for i in range(nrof_batches):
batch_size = min(nrof_examples - i * args.batch_size,
args.batch_size)
still_emb, lab = sess.run(
[embeddings, labels_batch],
feed_dict={
batch_size_placeholder: batch_size,
learning_rate_placeholder: lr,
phase_train_placeholder: True
})
still_emb_array[lab, :] = still_emb
print('%.3f' % (time.time() - start_time))
# Select triplets based on the embeddings
print('Selecting suitable triplets for training')
triplets, nrof_random_negs, nrof_triplets = tripletloss.select_triplets_cox(
video_emb_array, still_emb_array, num_per_class, video_paths,
still_paths, args.people_per_batch, args.alpha)
selection_time = time.time() - start_time
print(
'(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' %
(nrof_random_negs, nrof_triplets, selection_time))
# Perform training on the selected triplets
nrof_batches = int(np.ceil(nrof_triplets * 3 / args.batch_size))
triplet_paths = list(itertools.chain(*triplets))
labels_array = np.reshape(np.arange(len(triplet_paths)), (-1, 3))
triplet_paths_array = np.reshape(
np.expand_dims(np.array(triplet_paths), 1), (-1, 3))
sess.run(
enqueue_op, {
image_paths_placeholder: triplet_paths_array,
labels_placeholder: labels_array
})
nrof_examples = len(triplet_paths)
train_time = 0
i = 0
emb_array = np.zeros((nrof_examples, embedding_size))
loss_array = np.zeros((nrof_triplets, ))
summary = tf.Summary()
step = 0
while i < nrof_batches:
start_time = time.time()
batch_size = min(nrof_examples - i * args.batch_size,
args.batch_size)
feed_dict = {
batch_size_placeholder: batch_size,
learning_rate_placeholder: lr,
phase_train_placeholder: True
}
err, _, step, emb, lab = sess.run(
[loss, train_op, global_step, embeddings, labels_batch],
feed_dict=feed_dict)
#emb_array[lab,:] = emb
#loss_array[i] = err
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\tLoss %2.3f' %
(epoch, batch_number + 1, args.epoch_size, duration, err))
batch_number += 1
i += 1
train_time += duration
summary.value.add(tag='loss', simple_value=err)
# Add validation loss and accuracy to summary
#pylint: disable=maybe-no-member
summary.value.add(tag='time/selection', simple_value=selection_time)
summary_writer.add_summary(summary, step)
return step
def train(args, sess, dataset, epoch, image_paths_placeholder,
labels_placeholder, labels_batch, batch_size_placeholder,
learning_rate_placeholder, phase_train_placeholder, enqueue_op,
input_queue, global_step, embeddings, loss, train_op, summary_op,
summary_writer, learning_rate_schedule_file, embedding_size, anchor,
positive, negative, triplet_loss):
batch_number = 0
if args.learning_rate > 0.0:
lr = args.learning_rate
else:
lr = facenet.get_learning_rate_from_file(learning_rate_schedule_file,
epoch)
#下面的一个while循环运行一个批处理
while batch_number < args.epoch_size:
# Sample people randomly from the dataset
#默认下sample返回了1800，即1800个图像
image_paths, num_per_class = sample_people(dataset,
args.people_per_batch,
args.images_per_person)
#以上的输出里很多都是一张图片，那么这种肯定没有办法作为a和p，程序是怎么筛选出去的呢？
print('Running forward pass on sampled images: ', end='')
start_time = time.time()
nrof_examples = args.people_per_batch * args.images_per_person
# 根据默认参数，将输入的1800个图像变成了600*3的二维数据，如果不够1800张图像，可能要修改这里
labels_array = np.reshape(np.arange(nrof_examples),
(-1, 3)) #reshape(a,(-1,3))表示只给定列数为3,行数自行算出
image_paths_array = np.reshape(
np.expand_dims(np.array(image_paths), 1), (-1, 3))
#这里开辟了一个新的线程用于在内存里读取数据
sess.run(
enqueue_op, {
image_paths_placeholder: image_paths_array,
labels_placeholder: labels_array
})
# 默认的参数中，nrof_examples是1800，embedding_size是128
emb_array = np.zeros((nrof_examples, embedding_size))
# nrof_batches，默认是1800/90=20
nrof_batches = int(np.ceil(nrof_examples / args.batch_size))
# 批处理求特征，默认为20个批
for i in range(nrof_batches):
batch_size = min(nrof_examples - i * args.batch_size,
args.batch_size)
emb, lab = sess.run(
[embeddings, labels_batch],
feed_dict={
batch_size_placeholder: batch_size,
learning_rate_placeholder: lr,
phase_train_placeholder: True
})
emb_array[lab, :] = emb
print('%.3f' % (time.time() - start_time))
# Select triplets based on the embeddings
print('Selecting suitable triplets for training')
triplets, nrof_random_negs, nrof_triplets = select_triplets(
emb_array, num_per_class, image_paths, args.people_per_batch,
args.alpha)
selection_time = time.time() - start_time
print(
'(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' %
(nrof_random_negs, nrof_triplets, selection_time))
# Perform training on the selected triplets
nrof_batches = int(np.ceil(nrof_triplets * 3 / args.batch_size))
triplet_paths = list(itertools.chain(*triplets))
labels_array = np.reshape(np.arange(len(triplet_paths)), (-1, 3))
triplet_paths_array = np.reshape(
np.expand_dims(np.array(triplet_paths), 1), (-1, 3))
# 读取数据的操作
sess.run(
enqueue_op, {
image_paths_placeholder: triplet_paths_array,
labels_placeholder: labels_array
})
nrof_examples = len(triplet_paths)
train_time = 0
i = 0
emb_array = np.zeros((nrof_examples, embedding_size))
loss_array = np.zeros((nrof_triplets, ))
# 根据求出的特征计算triplet损失函数并进行优化
summary = tf.Summary()
while i < nrof_batches:
start_time = time.time()
batch_size = min(nrof_examples - i * args.batch_size,
args.batch_size)
feed_dict = {
batch_size_placeholder: batch_size,
learning_rate_placeholder: lr,
phase_train_placeholder: True
}
#sess run 有5个输入，fetches，先运行loss。前向计算的损失，train_op是根据损失来计算梯度，来对参数进行优化
err, _, step, emb, lab = sess.run(
[loss, train_op, global_step, embeddings, labels_batch],
feed_dict=feed_dict)
emb_array[lab, :] = emb
loss_array[i] = err
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\tLoss %2.3f' %
(epoch, batch_number + 1, args.epoch_size, duration, err))
batch_number += 1
i += 1
train_time += duration
summary.value.add(tag='loss', simple_value=err)
# Add validation loss and accuracy to summary
#pylint: disable=maybe-no-member
summary.value.add(tag='time/selection', simple_value=selection_time)
summary_writer.add_summary(summary, step)
return step
def train(args, sess, dataset, epoch, image_paths_placeholder, labels_placeholder, labels_batch,
batch_size_placeholder, learning_rate_placeholder, phase_train_placeholder, enqueue_op, input_queue, global_step,
embeddings, loss, train_op, summary_op, summary_writer, learning_rate_schedule_file,
embedding_size, anchor, positive, negative, triplet_loss):
batch_number = 0
if args.learning_rate>0.0:
lr = args.learning_rate
else:
lr = facenet.get_learning_rate_from_file(learning_rate_schedule_file, epoch)
while batch_number < args.epoch_size:
# Sample people randomly from the dataset
image_paths, num_per_class = sample_people(dataset, args.people_per_batch, args.images_per_person)
#image_paths = np.load('/home/xjyu/xhhu/facenet/npy_files/image_paths.npy')###xhhu
#for k in range(1,len(image_paths)): ###xhhu
# image_paths[k]=image_paths[0]###xhhu
#np.save('image_paths_ori.npy',image_paths)###xhhu
print('Running forward pass on sampled images: ', end='')
start_time = time.time()
nrof_examples = args.people_per_batch * args.images_per_person
labels_array = np.reshape(np.arange(nrof_examples),(-1,3))
image_paths_array = np.reshape(np.expand_dims(np.array(image_paths),1), (-1,3))
sess.run(enqueue_op, {image_paths_placeholder: image_paths_array, labels_placeholder: labels_array})
emb_array = np.zeros((nrof_examples, embedding_size))
nrof_batches = int(np.ceil(nrof_examples / args.batch_size))
for i in xrange(nrof_batches):
batch_size = min(nrof_examples-i*args.batch_size, args.batch_size)
emb, lab = sess.run([embeddings, labels_batch], feed_dict={batch_size_placeholder: batch_size,
learning_rate_placeholder: lr, phase_train_placeholder: True})
emb_array[lab,:] = emb
#np.save('emb_array_ori.npy',emb)###xhhu
#quit()###xhhu
print('time=%.3f seconds' % (time.time()-start_time))
# Select triplets based on the embeddings
print('Selecting suitable triplets for training')
triplets, nrof_random_negs, nrof_triplets = select_triplets(emb_array, num_per_class,
image_paths, args.people_per_batch, args.alpha, args.batch_size)
selection_time = time.time() - start_time
print('(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' %
(nrof_random_negs, nrof_triplets, selection_time))
# Perform training on the selected triplets
nrof_batches = int(np.ceil(nrof_triplets*3/args.batch_size))
triplet_paths = list(itertools.chain(*triplets))
labels_array = np.reshape(np.arange(len(triplet_paths)),(-1,3))
triplet_paths_array = np.reshape(np.expand_dims(np.array(triplet_paths),1), (-1,3))
sess.run(enqueue_op, {image_paths_placeholder: triplet_paths_array, labels_placeholder: labels_array})
nrof_examples = len(triplet_paths)
train_time = 0
i = 0
emb_array = np.zeros((nrof_examples, embedding_size)) #no use fbtian
loss_array = np.zeros((nrof_triplets,))#no use fbtian
while i < nrof_batches:
start_time = time.time()
batch_size = min(nrof_examples-i*args.batch_size, args.batch_size)
feed_dict = {batch_size_placeholder: batch_size, learning_rate_placeholder: lr, phase_train_placeholder: True}
err, _, step, emb, lab = sess.run([loss, train_op, global_step, embeddings, labels_batch], feed_dict=feed_dict)
#print(emb)
emb_array[lab,:] = emb #no use fbtian
loss_array[i] = err #no use fbtian
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\tLoss %2.5f' %
(epoch, batch_number+1, args.epoch_size, duration, err))
batch_number += 1
i += 1
train_time += duration
# Add validation loss and accuracy to summary
summary = tf.Summary()
#pylint: disable=maybe-no-member
summary.value.add(tag='time/selection', simple_value=selection_time)
summary_writer.add_summary(summary, step)
return step