def evaluate():
"""Eval KANJI for a single example"""
with tf.Graph().as_default() as g:
# Get images and labels for KANJI.
eval_data = FLAGS.eval_data == 'test'
images, labels = kanji.single_input(eval_data=eval_data)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = kanji.inference(images)
# Calculate predictions.
top_k_op = tf.nn.top_k(logits, k=5)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
kanji.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
while True:
eval_once(saver, top_k_op)
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
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 KANJI.
images, labels = kanji.distorted_inputs()
# Build inference Graph.
logits = kanji.inference(images)
# Build the portion of the Graph calculating the losses. Note that we will
# assemble the total_loss using a custom function below.
_ = kanji.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]*/' % kanji.TOWER_NAME, '', l.op.name)
tf.summary.scalar(loss_name, l)
return total_loss
def evaluate():
"""Eval KANJI for a number of steps."""
with tf.Graph().as_default() as g:
# Get images and labels for KANJI.
eval_data = FLAGS.eval_data == 'test'
images, labels = kanji.inputs(eval_data=eval_data)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = kanji.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(
kanji.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 generateGraph():
"""Generate the graph and its graphDef, freeze it, optimize it and then save it"""
with tf.Graph().as_default() as g:
# Get images and labels for KANJI.
eval_data = FLAGS.eval_data == 'test'
images, labels = kanji.single_input(eval_data=eval_data)
images2 = tf.reshape(images, [64, 64, 1])
images2 = tf.identity(images2, name='InputI')
images2 = tf.image.per_image_standardization(images2)
images2 = tf.reshape(images2, [1, 64, 64, 1])
# Build a Graph that computes the logits predictions from the
# inference model.
logits = kanji.inference(images2)
final_tensor = tf.add(logits, 0, name="finalresult")
generateFile()
def train():
"""Train KANJI for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels for kanjis.
images, labels = kanji.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = kanji.inference(images)
# Calculate loss.
loss = kanji.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = kanji.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.global_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# Build an initialization operation to run below.
init = tf.global_variables_initializer()
# 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.summary.FileWriter(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))
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)