def evaluate():
"""Eval CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
# get data off disk at random to validate
paths, labels = validation_data()
# get validation tensor: [batch_size, image_size, image_size, num_channels]
X, y = validation_tensor(paths, labels)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = models.xtal24_inference(X)
# Calculate predictions
top_k_op = tf.nn.in_top_k(logits, tf.to_int32(y, name='ToInt32'), 1)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
builder.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)
graph_def = tf.get_default_graph().as_graph_def()
# run validation
evaluations = eval_once(saver, top_k_op)
cm = confusion_matrix(zip(evaluations, paths, y))
print cm
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 = builder.distorted_inputs()
# Build inference Graph.
logits = models.xtal24_inference(images)
# Build the portion of the Graph calculating the losses. Note that we will
# assemble the total_loss using a custom function below.
_ = builder.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')
# Compute the moving average of all individual losses and the total loss.
loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
loss_averages_op = loss_averages.apply(losses + [total_loss])
# Attach a scalar summmary 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]*/' % builder.TOWER_NAME, '', l.op.name)
# Name each loss as '(raw)' and name the moving average version of the loss
# as the original loss name.
tf.scalar_summary(loss_name +' (raw)', l)
tf.scalar_summary(loss_name, loss_averages.average(l))
with tf.control_dependencies([loss_averages_op]):
total_loss = tf.identity(total_loss)
return total_loss
def train():
"""Train XTAL24 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels for CIFAR-10.
train_images, train_labels = builder.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
train_logits = models.xtal24_inference(train_images)
# will need to modify scope, in order to get this to work
# then, instead of having a test and train graph, the two
# graphs are shared
# Calculate loss.
loss = builder.loss(train_logits, train_labels)
# log accuracies on train / test
_accuracy_summary(train_logits, train_labels, train=True)
# _accuracy_summary(test_logits, train=False)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = builder.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.log_dir,
graph_def=sess.graph_def)
for step in xrange(FLAGS.maxiter):
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 summaries periodically
if step % FLAGS.summary_interval == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % FLAGS.parameter_interval == 0 or (step + 1) == FLAGS.maxiter:
checkpoint_path = os.path.join(FLAGS.log_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
