def train():
with tf.Graph().as_default():
global_step = tf.train.get_or_create_global_step()
with tf.device('/cpu:0'):
images, labels = adience.distored_inputs()
logits = adience.inference(images)
loss = adience.loss(logits, labels)
train_op = adience.train(loss, global_step)
class _LoggerHook(tf.train.SessionRunHook):
def begin(self):
self._step = -1
self._start_time = time.time()
def before_run(self, run_context):
self._step += 1
return tf.train.SessionRunArgs(loss)
def after_run(self, run_context, run_values):
if self._step % FLAGS.log_frequency == 0:
current_time = time.time()
duration = current_time - self._start_time
loss_value = run_values.results
examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
sec_per_batch = float(duration / FLAGS.log_frequency)
format_str = ('%s: step %d, loss = %.2f (%1.f examples/sec; %.3f ' 'sec/batch)')
print(format_str % (datetime.now(), self._step, loss_value, examples_per_sec, sec_per_batch))
with tf.train.MonitoredTrainingSession(
checkpoint_dir=FLAGS.train_dir,
hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
tf.train.NanTensorHook(loss),
_LoggerHook()],
config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement)) as mon_sess:
while not mon_sess.should_stop():
mon_sess.run(train_op)
def evaluate():
"""Eval CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
# Get images and labels for CIFAR-10.
eval_data = FLAGS.eval_data == 'test'
images, labels = adience.inputs(eval_data=eval_data)
FLAGS.num_examples = adience.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
# Build a Graph that computes the logits predictions from the
# inference model.
logits = adience.inference(images)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
adience.MOVING_AVERAGE_DECAY)
variables_to_restore = {}
for v in tf.all_variables():
if v in tf.trainable_variables():
restore_name = variable_averages.average_name(v)
else:
restore_name = v.op.name
variables_to_restore[restore_name] = v
saver = tf.train.Saver(variables_to_restore)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
graph_def = tf.get_default_graph().as_graph_def()
summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir, graph_def=graph_def)
while True:
eval_once(saver, summary_writer, top_k_op, summary_op)
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
def train(train_continue):
"""Train Adience for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels for Adience.
images, labels = adience.distorted_inputs()
print("distorted images")
#print(labels)
# Build a Graph that computes the logits predictions from the
# inference model.
print('call inference')
logits = adience.inference(images)
# Calculate loss.
print('call loss')
loss = adience.loss(logits, labels)
# Build a Grahalloph that trains the model with one batch of examples and
# updates the model parameters.
print('train_op')
train_op = adience.train(loss, global_step)
# 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)
# Create a saver.
if not train_continue:
saver = tf.train.Saver(tf.all_variables())
load_step = 0
else:
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
adience.MOVING_AVERAGE_DECAY)
variables_to_restore = {}
for v in tf.all_variables():
if v in tf.trainable_variables():
restore_name = variable_averages.average_name(v)
else:
restore_name = v.op.name
variables_to_restore[restore_name] = v
saver = tf.train.Saver(variables_to_restore)
ckpt = tf.train.get_checkpoint_state(FLAGS.train_dir)
if ckpt and ckpt.model_checkpoint_path:
print("Checkpoint found")
# Restores from checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
# Assuming model_checkpoint_path looks something like:
# /my-favorite-path/cifar10_train/model.ckpt-0,
# extract global_step from it.
load_step = int(ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]) + 1
print("Start from step: {}".format(load_step))
else:
print('No checkpoint file found')
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def)
for step in xrange(FLAGS.max_steps - load_step):
# continue
step += load_step
start_time = time.time()
_, loss_value = sess.run([train_op, loss])
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print (format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
else:
print("Step already over limit: {}".format(FLAGS.max_steps))