def evaluate():
"""Eval CIFAR-10 for a number of steps."""
with tf.Graph().as_default() as g:
# Get images and labels for CIFAR-10.
eval_data = FLAGS.eval_data == 'test'
images, labels = svhn.inputs(eval_data=eval_data)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = svhn.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(
svhn.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(FLAGS.eval_dir, g)
while True:
eval_once(saver, summary_writer, top_k_op, summary_op)
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
def evaluate():
"""Eval CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
# Get images and labels for CIFAR-10.
images, labels = inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = svhn.inference(images)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
top_k_predict_op = tf.argmax(logits, 1)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(svhn.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
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, top_k_predict_op, summary_op, images)
break
def tower_loss(scope):
"""Calculate the total loss on a single tower running the CIFAR model.
Args:
scope: unique prefix string identifying the CIFAR tower, e.g. 'tower_0'
Returns:
Tensor of shape [] containing the total loss for a batch of data
"""
# Get images and labels for CIFAR-10.
images, labels = svhn.distorted_inputs()
# Build inference Graph.
logits = svhn.inference(images)
# Build the portion of the Graph calculating the losses. Note that we will
# assemble the total_loss using a custom function below.
_ = svhn.loss(logits, labels)
# Assemble all of the losses for the current tower only.
losses = tf.get_collection('losses', scope)
# Calculate the total loss for the current tower.
total_loss = tf.add_n(losses, name='total_loss')
# Attach a scalar summary to all individual losses and the total loss; do the
# same for the averaged version of the losses.
for l in losses + [total_loss]:
# Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
# session. This helps the clarity of presentation on tensorboard.
loss_name = re.sub('%s_[0-9]*/' % svhn.TOWER_NAME, '', l.op.name)
tf.summary.scalar(loss_name, l)
return total_loss
def evaluate():
"""Eval CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
# Get images and labels for CIFAR-10.
images, labels = inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = svhn.inference(images)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
top_k_predict_op = tf.argmax(logits, 1)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
svhn.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
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, top_k_predict_op,
summary_op, images)
break
def train():
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels for CIFAR-10.
images, labels = svhn.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = svhn.inference(images)
# Calculate loss.
loss = svhn.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = svhn.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)
# 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):
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)
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.contrib.framework.get_or_create_global_step()
# Force input pipeline to CPU:0 to avoid operations sometimes ending up on
# GPU and resulting in a slow down.
with tf.device('/cpu:0'):
images, labels = svhn.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = svhn.inference(images)
# Calculate loss.
loss = svhn.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = svhn.train(loss, global_step)
class _LoggerHook(tf.train.SessionRunHook):
"""Logs loss and runtime."""
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) # Asks for loss value.
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
self._start_time = current_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 (%.1f 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 train():
"""Train SVHN for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels for SVHN with mat file
images, labels = svhn.distorted_inputs()
# Build a Graph that computes the logits predictions from
# inference model.
logits = svhn.inference(images)
# Calculate loss.
loss = svhn.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples
# and updates the model parm
train_op = svhn.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.all_variables())
# Build an initialization operation to run.
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)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
# summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
for step in xrange(FLAGS.max_steps):
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))
# 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)
def train_with_noise_ce(train_data, train_labels, ckpt_path):
tf.reset_default_graph()
with tf.Graph().as_default() as g:
train_data_shape = train_data.shape
# train_data_node = tf.placeholder(dtype=tf.float32, shape=[None, train_data_shape], name='train_data_node')
train_data_node = tf.placeholder(dtype=tf.float32,
shape=[
None, train_data_shape[1],
train_data_shape[2],
train_data_shape[3]
],
name='train_data_node')
train_labels_node = tf.placeholder(dtype=tf.float32,
shape=[None, 10],
name='test_labels_node')
print('placeholder done')
# logits = fc.inference(train_data_node)
# loss = fc.loss_fun(logits, train_labels_node)
if FLAGS.dataset == 'mnist':
logits = mlenet.inference(train_data_node)
loss = mlenet.loss_fun(logits, train_labels_node)
elif FLAGS.dataset == 'svhn':
logits = svhn.inference(train_data_node)
loss = svhn.loss_fun(logits, train_labels_node)
# print(loss.get_shape())
op = tf.train.AdamOptimizer(learning_rate=5e-4,
beta1=0.9,
beta2=0.999,
name="student_op").minimize(loss)
saver = tf.train.Saver(tf.global_variables())
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
data_length = len(train_data)
for step in xrange(FLAGS.max_steps):
start_time = time.time()
batch_indices = utils.random_batch_indices(data_length,
FLAGS.batch_size)
feed_dict = {
train_data_node: train_data[batch_indices],
train_labels_node: train_labels[batch_indices]
}
_, loss_value = sess.run([op, loss], feed_dict=feed_dict)
duration = time.time() - start_time
if step % 100 == 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, np.mean(loss_value),
examples_per_sec, sec_per_batch))
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
saver.save(sess, ckpt_path, global_step=step)
return True
def softmax_preds(images, ckpt_path, return_logits=False):
"""
Compute softmax activations (probabilities) with the model saved in the path
specified as an argument
:param images: a np array of images
:param ckpt_path: a TF model checkpoint
:param logits: if set to True, return logits instead of probabilities
:return: probabilities (or logits if logits is set to True)
"""
# Compute nb samples and deduce nb of batches
data_length = len(images)
nb_batches = math.ceil(len(images) / FLAGS.batch_size)
# Declare data placeholder
# train_data_node = tf.placeholder(dtype=tf.float32, shape=[None, images.shape[-1]])
train_data_node = tf.placeholder(
dtype=tf.float32,
shape=[None, images.shape[1], images.shape[2], images.shape[3]])
# Build a Graph that computes the logits predictions from the placeholder
# logits = fc.inference(train_data_node)
if FLAGS.dataset == 'mnist':
logits = mlenet.inference(train_data_node)
elif FLAGS.dataset == 'svhn':
logits = svhn.inference(train_data_node)
# logits = inference2(train_data_node)
if return_logits:
# We are returning the logits directly (no need to apply softmax)
output = logits
else:
# Add softmax predictions to graph: will return probabilities
output = tf.nn.softmax(logits)
# Restore the moving average version of the learned variables for eval.
# variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY)
# variables_to_restore = variable_averages.variables_to_restore()
# saver = tf.train.Saver(variables_to_restore)
saver = tf.train.Saver()
# Will hold the result
preds = np.zeros((data_length, 10), dtype=np.float32)
# Create TF session
with tf.Session() as sess:
# Restore TF session from checkpoint file
saver.restore(sess, ckpt_path)
# Parse data by batch
for batch_nb in xrange(0, int(nb_batches + 1)):
# Compute batch start and end indices
start, end = utils.batch_indices(batch_nb, data_length,
FLAGS.batch_size)
# Prepare feed dictionary
feed_dict = {train_data_node: images[start:end]}
# Run session ([0] because run returns a batch with len 1st dim == 1)
preds[start:end, :] = sess.run([output], feed_dict=feed_dict)[0]
# Reset graph to allow multiple calls
tf.reset_default_graph()
return preds
