我只在training（）中将我的损失概括为'xentropy_mean'，但是在张量板中，我没有找到'xentropy_mean'图表，但我没有找到许多其他图表。我不知道我写错了什么，确实是什么问题。是因为我在我的代码中使用线程吗？如果我不使用线程，我该怎么写呢？
The tensorboard screenshot 队列下有6个图表，我不知道是什么含义
我在下面的文件中创建模型
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import tensorflow.python.platform
import tensorflow as tf
# The MNIST dataset has 10 classes, representing the digits 0 through 9.
NUM_CLASSES = 16
# The MNIST images are always 28x28 pixels.
IMAGE_SIZE = 28
IMAGE_PIXELS = 784
def inference(images, hidden1_units, hidden2_units):
"""Build the MNIST model up to where it may be used for inference.
Args:
images: Images placeholder, from inputs().
hidden1_units: Size of the first hidden layer.
hidden2_units: Size of the second hidden layer.
Returns:
softmax_linear: Output tensor with the computed logits.
"""
# Hidden 1
with tf.name_scope('hidden1'):
weights = tf.Variable(
tf.truncated_normal([IMAGE_PIXELS, hidden1_units],
stddev=1.0 / math.sqrt(float(IMAGE_PIXELS))),
name='weights')
biases = tf.Variable(tf.zeros([hidden1_units]),
name='biases')
hidden1 = tf.nn.relu(tf.matmul(images, weights) + biases)
# Hidden 2
with tf.name_scope('hidden2'):
weights = tf.Variable(
tf.truncated_normal([hidden1_units, hidden2_units],
stddev=1.0 / math.sqrt(float(hidden1_units))),
name='weights')
biases = tf.Variable(tf.zeros([hidden2_units]),
name='biases')
hidden2 = tf.nn.relu(tf.matmul(hidden1, weights) + biases)
# Linear
with tf.name_scope('softmax_linear'):
weights = tf.Variable(
tf.truncated_normal([hidden2_units, NUM_CLASSES],
stddev=1.0 / math.sqrt(float(hidden2_units))),
name='weights')
biases = tf.Variable(tf.zeros([NUM_CLASSES]),
name='biases')
logits = tf.matmul(hidden2, weights) + biases
return logits
def loss(logits, labels):
batch_size = tf.size(labels)
#print('batch size %d' %(batch_size))
labels = tf.expand_dims(labels, 1)
indices = tf.expand_dims(tf.range(0, batch_size), 1)
concated = tf.concat(1, [indices, labels])
#print('Done2')
onehot_labels = tf.sparse_to_dense(
concated, tf.pack([batch_size, 16]), 1.0, 0.0)
#print('Done1')
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits,
onehot_labels,
name='xentropy')
loss = tf.reduce_mean(cross_entropy, name='xentropy_mean')
tf.summary.scalar(loss.op.name, loss)
return loss
def training(loss, learning_rate):
optimizer=tf.train.GradientDescentOptimizer(learning_rate)
global_step=tf.Variable(0,name='global_step',trainable=False)
train_op = optimizer.minimize(loss, global_step=global_step)
return train_op
def evaluation(logits, labels):
correct = tf.nn.in_top_k(logits, labels, 1)
# Return the number of true entries.
return tf.reduce_sum(tf.cast(correct, tf.int32))
并在此文件中训练模型：
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import os.path
import sys
import time
import numpy as np
import tensorflow as tf
import mnist
# Basic model parameters as external flags.
#FLAGS = None
# Constants used for dealing with the files, matches convert_to_records.
TRAIN_FILE = 'train.tfrecords'
VALIDATION_FILE = 'validation.tfrecords'
TEST_FILE='test.tfrecords'
flags = tf.app.flags
FLAGS = flags.FLAGS
#FLAGS = None
flags.DEFINE_string('train_dir', '/home/queenie/image2tfrecord/tfrecords-28-gray/', 'Directory to put the training data.')
flags.DEFINE_string('filename', 'train.tfrecords', 'Directory to put the training data.')
flags.DEFINE_integer('batch_size', 100, 'Batch size. '
'Must divide evenly into the dataset sizes.')
flags.DEFINE_integer('num_epochs', None, 'Batch size. '
'Must divide evenly into the dataset sizes.')
flags.DEFINE_integer('hidden1', 128,'balabala')
flags.DEFINE_integer('hidden2', 32,'balabala')
flags.DEFINE_integer('learning_rate', 0.01,'balabala')
flags.DEFINE_integer('max_steps', 50000,'balabala')
def placeholder_inputs(batch_size):
images_placeholder=tf.placeholder(tf.float32,shape=(batch_size,mnist.IMAGE_PIXELS))
labels_placeholder=tf.placeholder(tf.int32,shape=(batch_size))
return images_placeholder,labels_placeholder
def fill_feed_dict(images_feed,labels_feed,images_pl,labels_pl):
feed_dict={
images_pl:images_feed,
labels_pl:labels_feed,
}
return feed_dict
def read_and_decode(filename_queue):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
# Defaults are not specified since both keys are required.
features={
'image_raw': tf.FixedLenFeature([], tf.string),
'label': tf.FixedLenFeature([], tf.int64),
})
# Convert from a scalar string tensor (whose single string has
# length mnist.IMAGE_PIXELS) to a uint8 tensor with shape
# [mnist.IMAGE_PIXELS].
image = tf.decode_raw(features['image_raw'], tf.uint8)
image.set_shape([mnist.IMAGE_PIXELS])
# OPTIONAL: Could reshape into a 28x28 image and apply distortions
# here. Since we are not applying any distortions in this
# example, and the next step expects the image to be flattened
# into a vector, we don't bother.
# Convert from [0, 255] -> [-0.5, 0.5] floats.
image = tf.cast(image, tf.float32) * (1. / 255) - 0.5
# Convert label from a scalar uint8 tensor to an int32 scalar.
label = tf.cast(features['label'], tf.int32)
return image, label
def do_eval(sess,eval_correct):
true_count=0
for step in xrange(FLAGS.batch_size):
#print(sess.run(eval_correct))
true_count+=sess.run(eval_correct)
precision=float(true_count)/FLAGS.batch_size/FLAGS.batch_size
print(' Num examples: %d Num correct: %d Precision @ 1: %0.04f' %
(FLAGS.batch_size, true_count, precision))
return precision
def inputs(train, batch_size, num_epochs):
if not num_epochs: num_epochs = None
if train=='train':
filename=os.path.join(FLAGS.train_dir,TRAIN_FILE)
elif train=='validation':
filename=os.path.join(FLAGS.train_dir,VALIDATION_FILE)
else:
filename=os.path.join(FLAGS.train_dir,TEST_FILE)
# filename = os.path.join(FLAGS.train_dir,
# TRAIN_FILE if train else VALIDATION_FILE)
with tf.name_scope('input'):
filename_queue = tf.train.string_input_producer(
[filename], num_epochs=None)
# Even when reading in multiple threads, share the filename
# queue.
image, label = read_and_decode(filename_queue)
# Shuffle the examples and collect them into batch_size batches.
# (Internally uses a RandomShuffleQueue.)
# We run this in two threads to avoid being a bottleneck.
images, sparse_labels = tf.train.shuffle_batch(
[image, label], batch_size=batch_size, num_threads=2,
capacity=1000 + 3 * batch_size,
# Ensures a minimum amount of shuffling of examples.
min_after_dequeue=1000)
return images, sparse_labels
def run_training():
with tf.Graph().as_default():
# Build a Graph that computes predictions from the inference model.
images, labels = inputs(train='train', batch_size=FLAGS.batch_size,
num_epochs=FLAGS.num_epochs)
images_valid,labels_valid=inputs(train='validation', batch_size=FLAGS.batch_size,
num_epochs=FLAGS.num_epochs)
images_test,labels_test=inputs(train='test', batch_size=FLAGS.batch_size,
num_epochs=FLAGS.num_epochs)
logits = mnist.inference(images,
FLAGS.hidden1,
FLAGS.hidden2)
# Add to the Graph the loss calculation.
valid_prediction=mnist.inference(images_valid,FLAGS.hidden1,FLAGS.hidden2)
test_prediction=mnist.inference(images_test,FLAGS.hidden1,FLAGS.hidden2)
loss = mnist.loss(logits, labels)
# Add to the Graph operations that train the model.
train_op = mnist.training(loss, FLAGS.learning_rate)
eval_correct=mnist.evaluation(logits,labels)
eval_correct_valid=mnist.evaluation(valid_prediction,labels_valid)
eval_correct_test=mnist.evaluation(test_prediction,labels_test)
summary_op=tf.merge_all_summaries()
# The op for initializing the variables.
init_op = tf.group(tf.initialize_all_variables(),
tf.initialize_local_variables())
saver = tf.train.Saver()
# Create a session for running operations in the Graph.
sess = tf.Session()
# Initialize the variables (the trained variables and the
# epoch counter).
sess.run(init_op)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
# Start input enqueue threads.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
step = 0
train_precision=0
validation_precision=0
test_precision=0
#while not coord.should_stop():
while not coord.should_stop():
start_time = time.time()
_, loss_value,images_see,labels_see = sess.run([train_op, loss,images,labels])
#print('run done')
duration = time.time() - start_time
# Print an overview fairly often.
if step % 100 == 0:
print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value,
duration))
precision_tr=do_eval(sess,eval_correct)
summary_str=sess.run(summary_op)
summary_writer.add_summary(summary_str,step)
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_file = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_file, global_step=step)
print('Train:')
do_eval(sess,eval_correct)
print('Validation:')
do_eval(sess,eval_correct_valid)
print('Test:')
do_eval(sess,eval_correct_test)
step += 1
except tf.errors.OutOfRangeError:
print('Done training for %d epochs, %d steps.' % (FLAGS.num_epochs, step))
finally:
# When done, ask the threads to stop.
coord.request_stop()
# Wait for threads to finish.
coord.join(threads)
sess.close()
run_training()
然后我得到像这样的张量板，6个关于队列的图表。 The tensorboard screenshot
答案 0 :(得分：0)
您看到的队列图是默认情况下从shuffle_batch和朋友创建的，可用于监控输入管道的性能（理想情况下，您希望所有队列保持容量，因为这意味着您的GPU不是在输入阅读时阻止。
我不明白为什么你的摘要没有在张量板中显示。我可以获得更多信息吗？
