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()
# Get images and labels for CIFAR-10.
# 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 = general.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = general.inference(images)
# Calculate loss.
loss = general.loss(logits, labels)
#Calculate accuracy
accuracy = general.accuracy(logits, labels)
# updates the model parameters.
train_op = general.train(loss, global_step)
#builder = tf.saved_model.builder.SavedModelBuilder(general.MODEL_DIR) //can't save later in end() because the graph will be frozen after begin()
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, accuracy
]) # 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[0]
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))
if self._step % FLAGS.eval_frequency == 0:
accuracy = run_values.results[1]
print('%s: precision @ 1 = %.3f' %
(datetime.now(), accuracy))
#if self._step == FLAGS.max_steps -1:
#builder = run_values.results[2]
#def end(self, session):
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():
"""Run Eval once.
Args:
saver: Saver.
summary_writer: Summary writer.
top_k_op: Top K op.
summary_op: Summary op.
"""
with tf.Graph().as_default() as g:
# Get images and labels for CIFAR-10.
eval_data = FLAGS.eval_data == 'test'
images, labels = read_image.inputs(eval_data, FLAGS.eval_batch_size)
#这样居然也可以
FLAGS.batch_size = FLAGS.eval_batch_size
# Build a Graph that computes the logits predictions from the
# inference model.
logits = general.inference(images)
accuracy = general.accuracy(logits, labels)
# 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(
general.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)
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_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]
else:
print('No checkpoint file found')
return
summary_writer.add_graph(sess.graph)
# Start the queue runners.
coord = tf.train.Coordinator()
try:
threads = []
for qr in tf.get_collection(tf.GraphKeys.QUEUE_RUNNERS):
threads.extend(
qr.create_threads(sess,
coord=coord,
daemon=True,
start=True))
num_iter = int(
math.ceil(FLAGS.num_examples / FLAGS.eval_batch_size))
true_count = 0 # Counts the number of correct predictions.
total_sample_count = num_iter * FLAGS.batch_size
step = 0
accuracy_sum = 0
while step < num_iter and not coord.should_stop():
predictions = sess.run([top_k_op])
accuracy_sum += sess.run(accuracy)
true_count += np.sum(predictions)
step += 1
# Compute precision @ 1.
precision = true_count / total_sample_count
accuracy_avg = accuracy_sum / step
print('%s: precision @ 1 = %.4f' % (datetime.now(), precision))
print('%s: accuracy @ 1 = %.4f' %
(datetime.now(), accuracy_avg))
'''
2017-06-29 17:44:36.120575: precision @ 1 = 0.396
2017-06-29 17:44:36.120575: accuracy @ 1 = 0.411
真的不一样耶，为什么呢？随机吗？
'''
summary = tf.Summary()
summary.ParseFromString(sess.run(summary_op))
summary.value.add(tag='Precision @ 1', simple_value=precision)
summary_writer.add_summary(summary, global_step)
except Exception as e: # pylint: disable=broad-except
coord.request_stop(e)
coord.request_stop()
coord.join(threads, stop_grace_period_secs=10)