def evaluate():
with tf.Graph().as_default() as g:
eval_data = FLAGS.eval_data == 'test'
images, labels = convnet.inputs(eval_data=True)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = convnet.inference(images, eval=True)
loss = convnet.loss(logits, labels)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
#Compute confusion matrix
conf_mat = tf.contrib.metrics.confusion_matrix(
tf.arg_max(logits, 1), tf.cast(labels, tf.int64))
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
convnet.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()
summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir, g)
while True:
eval_once(saver, summary_writer, logits, labels, top_k_op,
conf_mat, loss, 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() as g:
# Get images and labels for CIFAR-10.
eval_data = FLAGS.eval_data == 'test'
images, labels = convnet.inputs(eval_data=True)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = convnet.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(
convnet.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()
summary_writer = tf.train.SummaryWriter(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():
with tf.Graph().as_default() as g:
eval_data = FLAGS.eval_data == 'test'
images, labels = convnet.inputs(eval_data=True)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = convnet.inference(images, eval=True)
loss = convnet.loss(logits, labels)
# Calculate r-squared measure
R_y = tf.reduce_sum(tf.square(labels - tf.squeeze(logits)))
R_e = tf.reduce_sum(
tf.square(labels - tf.reduce_mean(tf.squeeze(logits))))
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
convnet.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()
summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir, g)
while True:
eval_once(saver, summary_writer, logits, labels, loss, R_y, R_e,
summary_op)
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
def train():
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels.
images, labels = convnet.inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = convnet.inference(images)
# Calculate loss.
loss = convnet.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = convnet.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, 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)
if __name__ == '__main__':
train()
def train():
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels.
images, labels = convnet.inputs(eval_data=False)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = convnet.inference(images)
# Calculate loss.
loss = convnet.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = convnet.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)
# Load previously stored model from checkpoint
ckpt = tf.train.get_checkpoint_state(FLAGS.train_dir)
if ckpt and ckpt.model_checkpoint_path:
# 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.
global_step = ckpt.model_checkpoint_path.split('/')[-1].split(
'-')[-1]
print("Loading from checkpoint.Global step %s" % global_step)
else:
print("No checkpoint file found...Creating a new model...")
stepfile = "/home/soms/EmotionMusic/Model1/stepfile.txt"
if not os.path.exists(stepfile):
print("No step file found.")
step = 0
else:
f = open(stepfile, "r")
step = int(f.readlines()[0])
print("Step file step %d" % step)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
while step < FLAGS.max_steps:
start_time = time.time()
_, loss_value = sess.run([train_op, loss])
duration = time.time() - start_time
def signal_handler(signal, frame):
f = open(stepfile, 'w')
f.write(str(step))
print("Step file written to.")
sys.exit(0)
signal.signal(signal.SIGINT, signal_handler)
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 % 500 == 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)
step += 1