def train(args, sess, dataset, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer):
batch_number = 0
while batch_number < args.epoch_size:
print('Loading training data')
# Sample people and load new data
start_time = time.time()
image_paths, num_per_class = facenet.sample_people(dataset, args.people_per_batch, args.images_per_person)
image_data = facenet.load_data(image_paths, args.random_crop, args.random_flip, args.image_size)
load_time = time.time() - start_time
print('Loaded %d images in %.2f seconds' % (image_data.shape[0], load_time))
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = args.people_per_batch * args.images_per_person
nrof_batches_per_epoch = int(np.floor(nrof_examples_per_epoch / args.batch_size))
for i in xrange(nrof_batches_per_epoch):
batch = facenet.get_batch(image_data, args.batch_size, i)
feed_dict = {images_placeholder: batch, phase_train_placeholder: True}
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Select triplets based on the embeddings
triplets, nrof_random_negs, nrof_triplets = facenet.select_triplets(
emb_array, num_per_class, image_data, 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
train_time = 0
i = 0
while i * args.batch_size < nrof_triplets * 3 and batch_number < args.epoch_size:
start_time = time.time()
batch = facenet.get_triplet_batch(triplets, i, args.batch_size)
feed_dict = {images_placeholder: batch, phase_train_placeholder: True}
err, _, step = sess.run([loss, train_op, global_step], feed_dict=feed_dict)
if (batch_number % 20 == 0):
summary_str, step = sess.run([summary_op, global_step], feed_dict=feed_dict)
summary_writer.add_summary(summary_str, global_step=step)
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f' %
(epoch, batch_number, 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/load', simple_value=load_time)
summary.value.add(tag='time/selection', simple_value=selection_time)
summary.value.add(tag='time/train', simple_value=train_time)
summary.value.add(tag='time/total', simple_value=load_time+selection_time+train_time)
summary_writer.add_summary(summary, step)
return step
def train(args, sess, dataset, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer):
batch_number = 0
while batch_number < args.epoch_size:
print('Loading training data')
# Sample people and load new data
start_time = time.time()
image_paths, num_per_class = facenet.sample_people(dataset, args.people_per_batch, args.images_per_person)
image_data = facenet.load_data(image_paths, args.random_crop, args.random_flip, args.image_size)
load_time = time.time() - start_time
print('Loaded %d images in %.2f seconds' % (image_data.shape[0], load_time))
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = args.people_per_batch * args.images_per_person
nrof_batches_per_epoch = int(np.floor(nrof_examples_per_epoch / args.batch_size))
for i in xrange(nrof_batches_per_epoch):
batch = facenet.get_batch(image_data, args.batch_size, i)
feed_dict = {images_placeholder: batch, phase_train_placeholder: True}
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Select triplets based on the embeddings
triplets, nrof_random_negs, nrof_triplets = facenet.select_triplets(
emb_array, num_per_class, image_data, 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
train_time = 0
i = 0
while i * args.batch_size < nrof_triplets * 3 and batch_number < args.epoch_size:
start_time = time.time()
batch = facenet.get_triplet_batch(triplets, i, args.batch_size)
feed_dict = {images_placeholder: batch, phase_train_placeholder: True}
err, _, step = sess.run([loss, train_op, global_step], feed_dict=feed_dict)
if (batch_number % 20 == 0):
summary_str, step = sess.run([summary_op, global_step], feed_dict=feed_dict)
summary_writer.add_summary(summary_str, global_step=step)
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f' %
(epoch, batch_number, args.epoch_size, duration, err))
batch_number += 1
i += 1
train_time += duration
# Add validation loss and accuracy to summary
summary = tf.Summary()
summary.value.add(tag='time/load', simple_value=load_time)
summary.value.add(tag='time/selection', simple_value=selection_time)
summary.value.add(tag='time/train', simple_value=train_time)
summary.value.add(tag='time/total', simple_value=load_time+selection_time+train_time)
summary_writer.add_summary(summary, step)
return step
import numpy as np
import tensorflow as tf
import facenet
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_integer('people_per_batch', 45,
"""Number of people per batch.""")
tf.app.flags.DEFINE_integer(
'alpha', 0.2, """Positive to negative triplet distance margin.""")
embeddings = np.zeros((1800, 128))
np.random.seed(123)
for ix in range(embeddings.shape[0]):
for jx in range(embeddings.shape[1]):
rnd = 1.0 * np.random.randint(1, 2**32) / 2**32
embeddings[ix][jx] = rnd
emb_array = embeddings
image_data = np.zeros((1800, 96, 96, 3))
num_per_class = [40 for i in range(45)]
np.random.seed(123)
apn, nrof_random_negs, nrof_triplets = facenet.select_triplets(
emb_array, num_per_class, image_data)
def train():
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, test_set = facenet.split_dataset(dataset, 0.9)
fileName = "/home/david/debug4.h5"
f = h5py.File(fileName, "r")
for item in f.values():
print(item)
w1 = f['1w'][:]
b1 = f['1b'][:]
f.close()
print(w1.shape)
print(b1.shape)
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, 96, 96, 3), name='Input')
# Build a Graph that computes the logits predictions from the inference model
#embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, phase_train=True)
conv1 = _conv(images_placeholder, 3, 64, 7, 7, 2, 2, 'SAME', 'conv1_7x7', phase_train=False, use_batch_norm=False, init_weight=w1, init_bias=b1)
resh1 = tf.reshape(conv1, [-1, 294912])
embeddings = _affine(resh1, 294912, 128)
# Split example embeddings into anchor, positive and negative
a, p, n = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(a, p, n)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, grads = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def)
epoch = 0
with sess.as_default():
while epoch<FLAGS.max_nrof_epochs:
batch_number = 0
while batch_number<FLAGS.epoch_size:
print('Loading new data')
image_data, num_per_class, image_paths = facenet.load_data(train_set)
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = FLAGS.people_per_batch*FLAGS.images_per_person
nrof_batches_per_epoch = int(np.floor(nrof_examples_per_epoch/FLAGS.batch_size))
if True:
for i in xrange(nrof_batches_per_epoch):
feed_dict, _ = facenet.get_batch(images_placeholder, image_data, i)
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Select triplets based on the embeddings
apn, nrof_random_negs, nrof_triplets = facenet.select_triplets(emb_array, num_per_class, image_data)
duration = time.time() - start_time
print('(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds' % (nrof_random_negs, nrof_triplets, duration))
count = 0
while count<nrof_triplets*3 and batch_number<FLAGS.epoch_size:
start_time = time.time()
feed_dict, batch = facenet.get_batch(images_placeholder, apn, batch_number)
if (batch_number%20==0):
err, summary_str, _ = sess.run([loss, summary_op, train_op], feed_dict=feed_dict)
summary_writer.add_summary(summary_str, FLAGS.epoch_size*epoch+batch_number)
else:
err, _ = sess.run([loss, train_op], feed_dict=feed_dict)
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f' % (epoch, batch_number, FLAGS.epoch_size, duration, err))
batch_number+=1
count+=FLAGS.batch_size
else:
while batch_number<FLAGS.epoch_size:
start_time = time.time()
feed_dict, _ = facenet.get_batch(images_placeholder, image_data, batch_number)
grad_tensors, grad_vars = zip(*grads)
eval_list = (train_op, loss) + grad_tensors
result = sess.run(eval_list, feed_dict=feed_dict)
grads_eval = result[2:]
nrof_parameters = 0
for gt, gv in zip(grads_eval, grad_vars):
print('%40s: %6d' % (gv.op.name, np.size(gt)))
nrof_parameters += np.size(gt)
print('Total number of parameters: %d' % nrof_parameters)
err = result[1]
batch_number+=1
epoch+=1
# Save the model checkpoint periodically.
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=epoch*FLAGS.epoch_size+batch_number)
def train(args, sess, dataset, epoch, images_placeholder,
phase_train_placeholder, learning_rate_placeholder, global_step,
embeddings, loss, train_op, summary_op, summary_writer): #each epoch
batch_number = 0
if args.learning_rate > 0.0:
lr = args.learning_rate
else:
lr = get_learning_rate_from_file('../data/learning_rate_schedule.txt',
epoch)
while batch_number < args.epoch_size: #this batch_number means batch_num in train, not in getting feature
print('Loading training data')
# Sample people and load new data
start_time = time.time()
image_paths, num_per_class = facenet.sample_people(
dataset, args.people_per_epoch, args.images_per_person)
image_data = facenet.load_data(image_paths, args.random_crop,
args.random_flip, args.image_size)
load_time = time.time() - start_time
print('Loaded %d images in %.2f seconds' %
(image_data.shape[0], load_time))
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = args.people_per_epoch * args.images_per_person #have no connection with epoch_size
nrof_batches_per_epoch = int(
np.floor(nrof_examples_per_epoch / args.batch_size)
) #the variable is only for batched in getting feature
for i in xrange(nrof_batches_per_epoch):
batch = facenet.get_batch(image_data, args.batch_size, i)
feed_dict = {
images_placeholder: batch,
phase_train_placeholder: True,
learning_rate_placeholder: lr
}
emb_list += sess.run(
[embeddings], feed_dict=feed_dict
) #step 1:get the feature of all image in a epoch
emb_array = np.vstack(
emb_list
) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Select triplets based on the embeddings
# the data from lfw dataset makes the embeddings'size different from each other
triplets, nrof_random_negs, nrof_triplets = facenet.select_triplets(
emb_array, num_per_class, image_data, args.people_per_epoch,
args.alpha
) #Here the information from embedding and information from sample_people()
#print("num_triplets: "+str(len(triplets)))
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
train_time = 0
i = 0
#if tripplets is less than batch_size, go back to the start of the epoch
while i * args.batch_size < nrof_triplets * 3 and batch_number < args.epoch_size:
#Why not refresh the triplet every batch
start_time = time.time()
batch = facenet.get_triplet_batch(triplets, i, args.batch_size)
feed_dict = {
images_placeholder: batch,
phase_train_placeholder: True,
learning_rate_placeholder: lr
}
err, _, step = sess.run([loss, train_op, global_step],
feed_dict=feed_dict)
if (batch_number % 20 == 1):
#does the line below waste time?
summary_str, step = sess.run([summary_op, global_step],
feed_dict=feed_dict)
summary_writer.add_summary(summary_str, global_step=step)
duration = time.time() - start_time
print('Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f' %
(epoch, batch_number, 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/load', simple_value=load_time)
summary.value.add(tag='time/selection', simple_value=selection_time)
summary.value.add(tag='time/train', simple_value=train_time)
summary.value.add(tag='time/total',
simple_value=load_time + selection_time + train_time)
summary_writer.add_summary(summary, step)
return step
def train():
dataset = facenet.get_dataset(FLAGS.data_dir)
train_set, test_set = facenet.split_dataset(dataset, 0.9)
fileName = "/home/david/debug4.h5"
f = h5py.File(fileName, "r")
for item in f.values():
print(item)
w1 = f['1w'][:]
b1 = f['1b'][:]
f.close()
print(w1.shape)
print(b1.shape)
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32,
shape=(FLAGS.batch_size, 96, 96,
3),
name='Input')
# Build a Graph that computes the logits predictions from the inference model
#embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, phase_train=True)
conv1 = _conv(images_placeholder,
3,
64,
7,
7,
2,
2,
'SAME',
'conv1_7x7',
phase_train=False,
use_batch_norm=False,
init_weight=w1,
init_bias=b1)
resh1 = tf.reshape(conv1, [-1, 294912])
embeddings = _affine(resh1, 294912, 128)
# Split example embeddings into anchor, positive and negative
a, p, n = tf.split(0, 3, embeddings)
# Calculate triplet loss
loss = facenet.triplet_loss(a, p, n)
# Build a Graph that trains the model with one batch of examples and updates the model parameters
train_op, grads = facenet.train(loss, global_step)
# Create a saver
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
sess.run(init)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir,
graph_def=sess.graph_def)
epoch = 0
with sess.as_default():
while epoch < FLAGS.max_nrof_epochs:
batch_number = 0
while batch_number < FLAGS.epoch_size:
print('Loading new data')
image_data, num_per_class, image_paths = facenet.load_data(
train_set)
print('Selecting suitable triplets for training')
start_time = time.time()
emb_list = []
# Run a forward pass for the sampled images
nrof_examples_per_epoch = FLAGS.people_per_batch * FLAGS.images_per_person
nrof_batches_per_epoch = int(
np.floor(nrof_examples_per_epoch / FLAGS.batch_size))
if True:
for i in xrange(nrof_batches_per_epoch):
feed_dict, _ = facenet.get_batch(
images_placeholder, image_data, i)
emb_list += sess.run([embeddings],
feed_dict=feed_dict)
emb_array = np.vstack(
emb_list
) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Select triplets based on the embeddings
apn, nrof_random_negs, nrof_triplets = facenet.select_triplets(
emb_array, num_per_class, image_data)
duration = time.time() - start_time
print(
'(nrof_random_negs, nrof_triplets) = (%d, %d): time=%.3f seconds'
% (nrof_random_negs, nrof_triplets, duration))
count = 0
while count < nrof_triplets * 3 and batch_number < FLAGS.epoch_size:
start_time = time.time()
feed_dict, batch = facenet.get_batch(
images_placeholder, apn, batch_number)
if (batch_number % 20 == 0):
err, summary_str, _ = sess.run(
[loss, summary_op, train_op],
feed_dict=feed_dict)
summary_writer.add_summary(
summary_str,
FLAGS.epoch_size * epoch + batch_number)
else:
err, _ = sess.run([loss, train_op],
feed_dict=feed_dict)
duration = time.time() - start_time
print(
'Epoch: [%d][%d/%d]\tTime %.3f\ttripErr %2.3f'
% (epoch, batch_number, FLAGS.epoch_size,
duration, err))
batch_number += 1
count += FLAGS.batch_size
else:
while batch_number < FLAGS.epoch_size:
start_time = time.time()
feed_dict, _ = facenet.get_batch(
images_placeholder, image_data, batch_number)
grad_tensors, grad_vars = zip(*grads)
eval_list = (train_op, loss) + grad_tensors
result = sess.run(eval_list, feed_dict=feed_dict)
grads_eval = result[2:]
nrof_parameters = 0
for gt, gv in zip(grads_eval, grad_vars):
print('%40s: %6d' % (gv.op.name, np.size(gt)))
nrof_parameters += np.size(gt)
print('Total number of parameters: %d' %
nrof_parameters)
err = result[1]
batch_number += 1
epoch += 1
# Save the model checkpoint periodically.
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess,
checkpoint_path,
global_step=epoch * FLAGS.epoch_size + batch_number)
import facenet
import numpy as np
import tensorflow as tf
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_integer('people_per_batch', 45,
"""Number of people per batch.""")
tf.app.flags.DEFINE_integer('alpha', 0.2,
"""Positive to negative triplet distance margin.""")
embeddings = np.zeros((1800,128))
np.random.seed(123)
for ix in range(embeddings.shape[0]):
for jx in range(embeddings.shape[1]):
rnd = 1.0*np.random.randint(1,2**32)/2**32
embeddings[ix][jx] = rnd
emb_array = embeddings
image_data = np.zeros((1800,96,96,3))
num_per_class = [40 for i in range(45)]
np.random.seed(123)
apn, nrof_random_negs, nrof_triplets = facenet.select_triplets(emb_array, num_per_class, image_data)