def main(_):
FLAGS.batch_size = 1
pic_set = [
"F:/TensorFlowDev/PythonWorksp/TensorFlow/furniture/bed/baby-bed/baby-bed356.jpg",
"F:/TensorFlowDev/PythonWorksp/TensorFlow/furniture/bed/hammock/hammock1476.jpg",
"F:/TensorFlowDev/PythonWorksp/TensorFlow/RetrainInception/flower_photos/tulips/3150964108_24dbec4b23_m.jpg",
"F:/TensorFlowDev/PythonWorksp/TensorFlow/RetrainInception/flower_photos/tulips/3105702091_f02ce75226.jpg",
"F:/TensorFlowDev/www/upload-files/6454_14991605780.jpg",
"F:/TensorFlowDev/www/upload-files/4589_14991507381.jpg",
"F:/TensorFlowDev/www/upload-files/7255_14991507381.jpg",
"F:/TensorFlowDev/PythonWorksp/TensorFlow/furniture/bed/bunk-bed/bunk-bed576.jpg",
"F:/TensorFlowDev/www/upload-files/1501723500_05517.jpg",
"F:/TensorFlowDev/www/upload-files/1501723499_19721-n.jpg"
]
with tf.name_scope('input'): #
img_path = pic_set[9]
filename_queue = tf.train.string_input_producer([img_path]) #
reader = tf.WholeFileReader()
key, value = reader.read(filename_queue)
orig_img = tf.image.decode_jpeg(value)
print('here1')
resized_img = tf.image.resize_images(orig_img,
[IMAGE_SIZE, IMAGE_SIZE])
resized_img.set_shape((IMAGE_SIZE, IMAGE_SIZE, 3))
float_img = tf.image.per_image_standardization(resized_img)
image = tf.expand_dims(float_img, 0)
print('here2')
tf.summary.image('input-image', image)
#logits = general.inference(image)
action = general.inference(image)
# 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(
) #moving_avg_variables=tf.moving_average_variables() still lack somthing
#del variables_to_restore['input/vis-image/ExponentialMovingAverage']
#del variables_to_restore['input/vis-image/Adam_1']
#del variables_to_restore['train/beta2_power']
#del variables_to_restore['train/beta1_power']
#del variables_to_restore['input/vis-image/Adam']
saver = tf.train.Saver(variables_to_restore)
merged_summary = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(
FLAGS.vis_dir + img_path[img_path.rfind('/'):img_path.rfind('.')])
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
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)
#print(sess.run(image))
#hang forever?
# 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))
print(sess.run(action))
'''
pool1, argmax = sess.run(action)
raw = [[0 for x in range(FLAGS.batch_size)] for y in range(IMAGE_SIZE*IMAGE_SIZE*64)]
for i in range(int(IMAGE_SIZE/2)*int(IMAGE_SIZE/2)*64):
for j in range(FLAGS.batch_size):
raw[j][argmax[j][i]] = pool1[j][i]
unpooled = tf.conver_to_tensor(raw)
unpooled = tf.reshape(unpooled, [FLAGS.batch_size, IMAGE_SIZE, IMAGE_SIZE, 64])
unpooled_trans = general.deconv1(unpooled, kernel1)
tf.summary.image("reverse_pool1_discrete", unpooled_trans, max_outputs=16)
#neurons = tf.split(argmax, 64, axis=3)
#neurons = tf.squeeze(neurons)
#tf.summary.image("argmax_pool1", )
'''
summary = sess.run(merged_summary)
summary_writer.add_summary(summary, 0)
except Exception as e: # pylint: disable=broad-except
coord.request_stop(e)
coord.request_stop()
coord.join(threads, stop_grace_period_secs=10)
print('here3')
return
def main(_):
ps_hosts = FLAGS.ps_hosts.split(",")
worker_hosts = FLAGS.worker_hosts.split(",")
# Create a cluster from the parameter server and worker hosts.
cluster = tf.train.ClusterSpec({"ps": ps_hosts, "worker": worker_hosts})
# Create and start a server for the local task.
server = tf.train.Server(cluster,
job_name=FLAGS.job_name,
task_index=FLAGS.task_index)
if FLAGS.job_name == "ps":
server.join()
elif FLAGS.job_name == "worker":
# Assigns ops to the local worker by default.
with tf.device(tf.train.replica_device_setter(
worker_device="/job:worker/task:%d" % FLAGS.task_index,
cluster=cluster)):
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)
global_step = tf.contrib.framework.get_or_create_global_step()
train_op = tf.train.AdagradOptimizer(0.01).minimize(
loss, global_step=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 % 20 == 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 = 20 * 128 / duration
sec_per_batch = float(duration / 20)
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))
# The StopAtStepHook handles stopping after running given steps.
hooks=[tf.train.StopAtStepHook(last_step=1000),_LoggerHook()]
# The MonitoredTrainingSession takes care of session initialization,
# restoring from a checkpoint, saving to a checkpoint, and closing when done
# or an error occurs.
with tf.train.MonitoredTrainingSession(master=server.target,
is_chief=(FLAGS.task_index == 0),
checkpoint_dir="./logs/train_logs",
hooks=hooks) as mon_sess:
while not mon_sess.should_stop():
# Run a training step asynchronously.
# See `tf.train.SyncReplicasOptimizer` for additional details on how to
# perform *synchronous* training.
# mon_sess.run handles AbortedError in case of preempted PS.
mon_sess.run(train_op)
def build_and_save(images, builder, output_graph):
# Build a Graph that computes the logits predictions from the
# inference model.
logits = general.inference(images)
# 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)
merged_summary = tf.summary.merge_all()
# Build the summary operation based on the TF collection of Summaries.
#summary_op = tf.summary.merge_all()
# Before exporting our graph, we need to precise what is our output node
# This is how TF decides what part of the Graph he has to keep and what part it can dump
# NOTE: this variable is plural, because you can have multiple output nodes
output_node_names = "softmax_linear/softmax_linear"
# We clear devices to allow TensorFlow to control on which device it will load operations
clear_devices = True
summary_writer = tf.summary.FileWriter(FLAGS.save_dir)
graph = tf.get_default_graph()
input_graph_def = graph.as_graph_def()
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))
# We use a built-in TF helper to export variables to constants
output_graph_def = graph_util.convert_variables_to_constants(
sess, # The session is used to retrieve the weights
input_graph_def, # The graph_def is used to retrieve the nodes
output_node_names.split(
","
) # The output node names are used to select the usefull nodes
)
# Finally we serialize and dump the output graph to the filesystem
with tf.gfile.GFile(output_graph, "wb") as f:
f.write(output_graph_def.SerializeToString())
print("%d ops in the final graph." % len(output_graph_def.node))
#什么也不干
builder.add_meta_graph_and_variables(
sess, [tf.saved_model.tag_constants.SERVING])
#builder.save(True)
builder.save()
except Exception as e: # pylint: disable=broad-except
coord.request_stop(e)
coord.request_stop()
coord.join(threads, stop_grace_period_secs=10)
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)
