def main(_):
with open('{}/jobs/job{}.txt'.format(FLAGS.PATH_TO_HACONE, FLAGS.name_job),
'r') as fp:
data = json.load(fp)
job_id = data['job']
params = data['params']
params = json.loads(params)
if not FLAGS.output_file:
raise ValueError(
'You must supply the path to save to with --output_file')
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default() as graph:
dataset = dataset_factory.get_dataset(FLAGS.dataset_name, 'train',
FLAGS.dataset_dir)
candidate = []
print("main")
#print(tf.app.flags.FLAGS.train_dir)
for i in xrange(0, 5):
candidate.append(params['b{}_i1'.format(i)])
candidate.append(params['b{}_i2'.format(i)])
candidate.append(params['b{}_o1'.format(i)])
candidate.append(params['b{}_o2'.format(i)])
print(candidate)
N = 2
F = 24
network_fn = nets_factory.get_network_fn(
FLAGS.model_name,
candidate,
N,
F,
num_classes=(dataset.num_classes - FLAGS.labels_offset),
is_training=FLAGS.is_training)
image_size = FLAGS.image_size or network_fn.default_image_size
placeholder = tf.placeholder(
name='input',
dtype=tf.float32,
shape=[FLAGS.batch_size, image_size, image_size, 3])
network_fn(placeholder)
graph_def = graph.as_graph_def()
with gfile.GFile(FLAGS.output_file, 'wb') as f:
f.write(graph_def.SerializeToString())
def main(model_name, N, F):
PATH_TO_HACONE = '/home/lile/Projects/git_repo/hacone'
final_model_name = model_name + '_N{}_F{}'.format(N, F)
output_file = PATH_TO_HACONE + '/outputs/final_models/{}/inference_graph.pb'.format(
final_model_name)
with open('{}/jobs/job{}.txt'.format(PATH_TO_HACONE, model_name),
'r') as fp:
data = json.load(fp)
job_id = data['job']
params = data['params']
params = json.loads(params)
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default() as graph:
dataset = dataset_factory.get_dataset('cifar10', 'test',
'/home/lile/dataset/cifar10')
candidate = []
print("main")
#print(tf.app.flags.FLAGS.train_dir)
for i in xrange(0, 5):
candidate.append(params['b{}_i1'.format(i)])
candidate.append(params['b{}_i2'.format(i)])
candidate.append(params['b{}_o1'.format(i)])
candidate.append(params['b{}_o2'.format(i)])
print(candidate)
network_fn = nets_factory.get_network_fn(
'cifarnet',
candidate,
N,
F,
num_classes=(dataset.num_classes - 0),
is_training=False)
image_size = network_fn.default_image_size
placeholder = tf.placeholder(name='input',
dtype=tf.float32,
shape=[None, image_size, image_size, 3])
network_fn(placeholder)
graph_def = graph.as_graph_def()
with gfile.GFile(output_file, 'wb') as f:
f.write(graph_def.SerializeToString())
def main(_):
if not FLAGS.output_file:
raise ValueError('You must supply the path to save to with --output_file')
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default() as graph:
dataset = dataset_factory.get_dataset(FLAGS.dataset_name, 'train',
FLAGS.dataset_dir)
candidate = [-1, -1, 0, 3, -1, -1, 0, 3, -1, -1, 0, 3, -1, -1, 0, 3, -1, -1, 0, 3]
network_fn = nets_factory.get_network_fn(
FLAGS.model_name, candidate,
num_classes=(dataset.num_classes - FLAGS.labels_offset),
is_training=FLAGS.is_training)
image_size = FLAGS.image_size or network_fn.default_image_size
placeholder = tf.placeholder(name='input', dtype=tf.float32,
shape=[FLAGS.batch_size, image_size,
image_size, 3])
network_fn(placeholder)
graph_def = graph.as_graph_def()
with gfile.GFile(FLAGS.output_file, 'wb') as f:
f.write(graph_def.SerializeToString())
def eval_model(candidate, N, F):
print("eval model")
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default():
tf_global_step = slim.get_or_create_global_step()
######################
# Select the dataset #
######################
dataset = dataset_factory.get_dataset(FLAGS.dataset_name, 'val',
FLAGS.dataset_dir)
####################
# Select the model #
####################
network_fn = nets_factory.get_network_fn(
FLAGS.model_name,
candidate,
N,
F,
num_classes=(dataset.num_classes - FLAGS.labels_offset),
is_training=False)
##############################################################
# Create a dataset provider that loads data from the dataset #
##############################################################
provider = slim.dataset_data_provider.DatasetDataProvider(
dataset,
shuffle=False,
common_queue_capacity=2 * FLAGS.batch_size,
common_queue_min=FLAGS.batch_size)
[image, label] = provider.get(['image', 'label'])
label -= FLAGS.labels_offset
#####################################
# Select the preprocessing function #
#####################################
preprocessing_name = FLAGS.preprocessing_name or FLAGS.model_name
image_preprocessing_fn = preprocessing_factory.get_preprocessing(
preprocessing_name, is_training=False)
eval_image_size = network_fn.default_image_size
image = image_preprocessing_fn(image, eval_image_size, eval_image_size)
FLAGS.batch_size = 100
images, labels = tf.train.batch(
[image, label],
batch_size=FLAGS.batch_size,
num_threads=FLAGS.num_preprocessing_threads,
capacity=5 * FLAGS.batch_size)
####################
# Define the model #
####################
logits, _ = network_fn(images)
if FLAGS.moving_average_decay:
variable_averages = tf.train.ExponentialMovingAverage(
FLAGS.moving_average_decay, tf_global_step)
variables_to_restore = variable_averages.variables_to_restore(
slim.get_model_variables())
variables_to_restore[tf_global_step.op.name] = tf_global_step
else:
variables_to_restore = slim.get_variables_to_restore()
predictions = tf.argmax(logits, 1)
labels = tf.squeeze(labels)
# Define the metrics:
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'Accuracy':
slim.metrics.streaming_accuracy(predictions, labels),
'Recall_5':
slim.metrics.streaming_recall_at_k(logits, labels, 5),
})
# Print the summaries to screen.
for name, value in names_to_values.items():
summary_name = 'eval/%s' % name
op = tf.summary.scalar(summary_name, value, collections=[])
op = tf.Print(op, [value], summary_name)
tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
# TODO(sguada) use num_epochs=1
if FLAGS.max_num_batches:
num_batches = FLAGS.max_num_batches
else:
# This ensures that we make a single pass over all of the data.
num_batches = math.ceil(dataset.num_samples /
float(FLAGS.batch_size))
FLAGS.checkpoint_path = FLAGS.train_dir
if tf.gfile.IsDirectory(FLAGS.checkpoint_path):
checkpoint_path = tf.train.latest_checkpoint(FLAGS.checkpoint_path)
else:
checkpoint_path = FLAGS.checkpoint_path
tf.logging.info('Evaluating %s' % checkpoint_path)
final_op = [names_to_values['Accuracy']] #top1 accuracy to return
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
start_time = time.time()
a = slim.evaluation.evaluate_once(
master=FLAGS.master,
checkpoint_path=checkpoint_path,
logdir=FLAGS.eval_dir,
session_config=config,
num_evals=num_batches,
eval_op=list(names_to_updates.values()),
final_op=final_op,
variables_to_restore=variables_to_restore)
duration = time.time() - start_time
print('________________________________')
print('duration :' + str(duration))
print('________________________________')
return duration
def train_model(candidate, N, F):
print("train model")
print(FLAGS.dataset_name)
if not FLAGS.dataset_dir:
raise ValueError(
'You must supply the dataset directory with --dataset_dir')
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default():
#######################
# Config model_deploy #
#######################
deploy_config = model_deploy.DeploymentConfig(
num_clones=FLAGS.num_clones,
clone_on_cpu=FLAGS.clone_on_cpu,
replica_id=FLAGS.task,
num_replicas=FLAGS.worker_replicas,
num_ps_tasks=FLAGS.num_ps_tasks)
# Create global_step
with tf.device(deploy_config.variables_device()):
global_step = slim.create_global_step()
######################
# Select the dataset #
######################
dataset = dataset_factory.get_dataset(FLAGS.dataset_name,
FLAGS.dataset_split_name,
FLAGS.dataset_dir)
######################
# Select the network #
######################
network_fn = nets_factory.get_network_fn(
FLAGS.model_name,
candidate,
N,
F,
num_classes=(dataset.num_classes - FLAGS.labels_offset),
weight_decay=FLAGS.weight_decay,
is_training=True)
#####################################
# Select the preprocessing function #
#####################################
preprocessing_name = FLAGS.preprocessing_name or FLAGS.model_name
image_preprocessing_fn = preprocessing_factory.get_preprocessing(
preprocessing_name, is_training=True)
##############################################################
# Create a dataset provider that loads data from the dataset #
##############################################################
with tf.device(deploy_config.inputs_device()):
provider = slim.dataset_data_provider.DatasetDataProvider(
dataset,
num_readers=FLAGS.num_readers,
common_queue_capacity=20 * FLAGS.batch_size,
common_queue_min=10 * FLAGS.batch_size)
[image, label] = provider.get(['image', 'label'])
label -= FLAGS.labels_offset
train_image_size = FLAGS.train_image_size or network_fn.default_image_size
image = image_preprocessing_fn(image, train_image_size,
train_image_size)
images, labels = tf.train.batch(
[image, label],
batch_size=FLAGS.batch_size,
num_threads=FLAGS.num_preprocessing_threads,
capacity=5 * FLAGS.batch_size)
labels = slim.one_hot_encoding(
labels, dataset.num_classes - FLAGS.labels_offset)
batch_queue = slim.prefetch_queue.prefetch_queue(
[images, labels], capacity=2 * deploy_config.num_clones)
####################
# Define the model #
####################
def clone_fn(batch_queue):
"""Allows data parallelism by creating multiple clones of network_fn."""
images, labels = batch_queue.dequeue()
logits, end_points = network_fn(images)
#############################
# Specify the loss function #
#############################
if 'AuxLogits' in end_points:
slim.losses.softmax_cross_entropy(
end_points['AuxLogits'],
labels,
label_smoothing=FLAGS.label_smoothing,
weights=0.4,
scope='aux_loss')
slim.losses.softmax_cross_entropy(
logits,
labels,
label_smoothing=FLAGS.label_smoothing,
weights=1.0)
return end_points
# Gather initial summaries.
summaries = set(tf.get_collection(tf.GraphKeys.SUMMARIES))
clones = model_deploy.create_clones(deploy_config, clone_fn,
[batch_queue])
first_clone_scope = deploy_config.clone_scope(0)
# Gather update_ops from the first clone. These contain, for example,
# the updates for the batch_norm variables created by network_fn.
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS,
first_clone_scope)
# Add summaries for end_points.
end_points = clones[0].outputs
for end_point in end_points:
x = end_points[end_point]
summaries.add(tf.summary.histogram('activations/' + end_point, x))
summaries.add(
tf.summary.scalar('sparsity/' + end_point,
tf.nn.zero_fraction(x)))
# Add summaries for losses.
for loss in tf.get_collection(tf.GraphKeys.LOSSES, first_clone_scope):
summaries.add(tf.summary.scalar('losses/%s' % loss.op.name, loss))
# Add summaries for variables.
for variable in slim.get_model_variables():
summaries.add(tf.summary.histogram(variable.op.name, variable))
#################################
# Configure the moving averages #
#################################
if FLAGS.moving_average_decay:
moving_average_variables = slim.get_model_variables()
variable_averages = tf.train.ExponentialMovingAverage(
FLAGS.moving_average_decay, global_step)
else:
moving_average_variables, variable_averages = None, None
#########################################
# Configure the optimization procedure. #
#########################################
with tf.device(deploy_config.optimizer_device()):
learning_rate = _configure_learning_rate(dataset.num_samples,
global_step)
optimizer = _configure_optimizer(learning_rate)
summaries.add(tf.summary.scalar('learning_rate', learning_rate))
if FLAGS.sync_replicas:
# If sync_replicas is enabled, the averaging will be done in the chief
# queue runner.
optimizer = tf.train.SyncReplicasOptimizer(
opt=optimizer,
replicas_to_aggregate=FLAGS.replicas_to_aggregate,
total_num_replicas=FLAGS.worker_replicas,
variable_averages=variable_averages,
variables_to_average=moving_average_variables)
elif FLAGS.moving_average_decay:
# Update ops executed locally by trainer.
update_ops.append(
variable_averages.apply(moving_average_variables))
# Variables to train.
variables_to_train = _get_variables_to_train()
# and returns a train_tensor and summary_op
total_loss, clones_gradients = model_deploy.optimize_clones(
clones, optimizer, var_list=variables_to_train)
# Add total_loss to summary.
summaries.add(tf.summary.scalar('total_loss', total_loss))
# Create gradient updates.
grad_updates = optimizer.apply_gradients(clones_gradients,
global_step=global_step)
update_ops.append(grad_updates)
update_op = tf.group(*update_ops)
with tf.control_dependencies([update_op]):
train_tensor = tf.identity(total_loss, name='train_op')
# Add the summaries from the first clone. These contain the summaries
# created by model_fn and either optimize_clones() or _gather_clone_loss().
summaries |= set(
tf.get_collection(tf.GraphKeys.SUMMARIES, first_clone_scope))
# Merge all summaries together.
summary_op = tf.summary.merge(list(summaries), name='summary_op')
###########################
# Kicks off the training. #
###########################
slim.learning.train(
train_tensor,
logdir=FLAGS.train_dir,
master=FLAGS.master,
is_chief=(FLAGS.task == 0),
init_fn=_get_init_fn(),
summary_op=summary_op,
number_of_steps=FLAGS.max_number_of_steps,
log_every_n_steps=FLAGS.log_every_n_steps,
save_summaries_secs=FLAGS.save_summaries_secs,
save_interval_secs=FLAGS.save_interval_secs,
sync_optimizer=optimizer if FLAGS.sync_replicas else None)
def eval_model(model_name):
slim = tf.contrib.slim
print("eval model")
PATH_TO_HACONE_LOCAL = '/home/lile/Projects/git_repo/hacone'
with open(PATH_TO_HACONE_LOCAL +
'/jobs/job{}.txt'.format(model_name)) as fp:
data = json.load(fp)
job_id = data['job']
params = data['params']
params = json.loads(params)
candidate = []
for i in xrange(0, 5):
candidate.append(params['b{}_i1'.format(i)])
candidate.append(params['b{}_i2'.format(i)])
candidate.append(params['b{}_o1'.format(i)])
candidate.append(params['b{}_o2'.format(i)])
N = 2
F = 24
dataset_dir = '/home/lile/dataset/cifar10_val'
batch_size = 100
output_dir = os.path.join(PATH_TO_HACONE_LOCAL, 'models_trained',
model_name)
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default():
tf_global_step = slim.get_or_create_global_step()
######################
# Select the dataset #
######################
dataset = dataset_factory.get_dataset('cifar10', 'val', dataset_dir)
####################
# Select the model #
####################
network_fn = nets_factory.get_network_fn(
'cifarnet',
candidate,
N,
F,
num_classes=(dataset.num_classes - 0),
is_training=False)
##############################################################
# Create a dataset provider that loads data from the dataset #
##############################################################
provider = slim.dataset_data_provider.DatasetDataProvider(
dataset,
shuffle=False,
common_queue_capacity=2 * batch_size,
common_queue_min=batch_size)
[image, label] = provider.get(['image', 'label'])
#####################################
# Select the preprocessing function #
#####################################
preprocessing_name = 'cifarnet'
image_preprocessing_fn = preprocessing_factory.get_preprocessing(
preprocessing_name, is_training=False)
eval_image_size = network_fn.default_image_size
image = image_preprocessing_fn(image, eval_image_size, eval_image_size)
images, labels = tf.train.batch([image, label],
batch_size=batch_size,
num_threads=4,
capacity=5 * batch_size)
####################
# Define the model #
####################
logits, _ = network_fn(images)
variables_to_restore = slim.get_variables_to_restore()
predictions = tf.argmax(logits, 1)
labels = tf.squeeze(labels)
# Define the metrics:
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'Accuracy':
slim.metrics.streaming_accuracy(predictions, labels),
'Recall_5':
slim.metrics.streaming_recall_at_k(logits, labels, 5),
})
# Print the summaries to screen.
for name, value in names_to_values.items():
summary_name = 'eval/%s' % name
op = tf.summary.scalar(summary_name, value, collections=[])
op = tf.Print(op, [value], summary_name)
tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
# TODO(sguada) use num_epochs=1
num_batches = math.ceil(dataset.num_samples / float(batch_size))
checkpoint_path = output_dir
if tf.gfile.IsDirectory(checkpoint_path):
checkpoint_path = tf.train.latest_checkpoint(checkpoint_path)
else:
checkpoint_path = checkpoint_path
tf.logging.info('Evaluating %s' % checkpoint_path)
final_op = [names_to_values['Accuracy']] #top1 accuracy to return
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
start_time = time.time()
a = slim.evaluation.evaluate_once(
master='',
checkpoint_path=checkpoint_path,
logdir=output_dir,
session_config=config,
num_evals=num_batches,
eval_op=list(names_to_updates.values()),
final_op=final_op,
variables_to_restore=variables_to_restore)
duration = time.time() - start_time
print('________________________________')
print('duration :' + str(duration))
print('________________________________')
print(a)
return duration
