我试图在TensorFlow模型库中修改CIFAR-10教程以提供自定义数据并自定义训练参数和图层，我有3个卷积层和2个完全连接的图层。我的训练数据有2310个24x24灰度图像，它在我将优化器更改为AdamOptimizer之前工作正常，但现在我得到了一些错误，在我将优化器更改回GradientDescentOptimizer之后甚至没有解决：
cro@deep03:~/image/cifar10_mod$ python3 cifar10_train.py
Filling queue with 924 CIFAR images before starting to train. This will take a few minutes.
2017-07-19 17:26:55.586361: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 17:26:55.586379: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 17:26:55.586386: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 17:26:55.586391: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 17:26:55.586412: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 17:26:55.697215: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:893] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2017-07-19 17:26:55.697464: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties:
name: GeForce GTX 1060 6GB
major: 6 minor: 1 memoryClockRate (GHz) 1.7845
pciBusID 0000:01:00.0
Total memory: 5.93GiB
Free memory: 5.80GiB
2017-07-19 17:26:55.697475: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0
2017-07-19 17:26:55.697479: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0: Y
2017-07-19 17:26:55.697484: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0)
2017-07-19 17:26:56.594088: W tensorflow/core/framework/op_kernel.cc:1158] Invalid argument: Nan in summary histogram for: softmax_linear/biases/gradients
[[Node: softmax_linear/biases/gradients = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](softmax_linear/biases/gradients/tag, gradients/softmax_linear/softmax_linear_grad/tuple/control_dependency_1/_285)]]
InvalidArgumentError (see above for traceback): Nan in summary histogram for: softmax_linear/biases/gradients
[[Node: softmax_linear/biases/gradients = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](softmax_linear/biases/gradients/tag, gradients/softmax_linear/softmax_linear_grad/tuple/control_dependency_1/_285)]]
cro@deep03:~/image/cifar10_mod$
这是我的代码：
文件cifar10.py：
# pylint: disable=missing-docstring
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import re
import sys
import tarfile
from six.moves import urllib
import tensorflow as tf
import cifar10_input
FLAGS = tf.app.flags.FLAGS
# Basic model parameters.
tf.app.flags.DEFINE_integer('batch_size', 100,
"""Number of images to process in a batch.""")
tf.app.flags.DEFINE_string('data_dir', '/tmp/cifar10_data',
"""Path to the CIFAR-10 data directory.""")
tf.app.flags.DEFINE_boolean('use_fp16', False,
"""Train the model using fp16.""")
# Global constants describing the CIFAR-10 data set.
IMAGE_SIZE = cifar10_input.IMAGE_SIZE
NUM_CLASSES = cifar10_input.NUM_CLASSES
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = cifar10_input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = cifar10_input.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
# Constants describing the training process.
MOVING_AVERAGE_DECAY = 0.9999 # The decay to use for the moving average.
NUM_EPOCHS_PER_DECAY = 50.0 # Epochs after which learning rate decays.
LEARNING_RATE_DECAY_FACTOR = 0.1 # Learning rate decay factor.
INITIAL_LEARNING_RATE = 0.1 # Initial learning rate.
# If a model is trained with multiple GPUs, prefix all Op names with tower_name
# to differentiate the operations. Note that this prefix is removed from the
# names of the summaries when visualizing a model.
TOWER_NAME = 'tower'
DATA_URL = 'http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz'
def _activation_summary(x):
"""Helper to create summaries for activations.
Creates a summary that provides a histogram of activations.
Creates a summary that measures the sparsity of activations.
Args:
x: Tensor
Returns:
nothing
"""
# Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
# session. This helps the clarity of presentation on tensorboard.
tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name)
tf.summary.histogram(tensor_name + '/activations', x)
tf.summary.scalar(tensor_name + '/sparsity',
tf.nn.zero_fraction(x))
def _variable_on_cpu(name, shape, initializer):
"""Helper to create a Variable stored on CPU memory.
Args:
name: name of the variable
shape: list of ints
initializer: initializer for Variable
Returns:
Variable Tensor
"""
with tf.device('/cpu:0'):
dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
var = tf.get_variable(name, shape, initializer=initializer, dtype=dtype)
return var
def _variable_with_weight_decay(name, shape, stddev, wd):
"""Helper to create an initialized Variable with weight decay.
Note that the Variable is initialized with a truncated normal distribution.
A weight decay is added only if one is specified.
Args:
name: name of the variable
shape: list of ints
stddev: standard deviation of a truncated Gaussian
wd: add L2Loss weight decay multiplied by this float. If None, weight
decay is not added for this Variable.
Returns:
Variable Tensor
"""
dtype = tf.float16 if FLAGS.use_fp16 else tf.float32
var = _variable_on_cpu(
name,
shape,
tf.truncated_normal_initializer(stddev=stddev, dtype=dtype))
if wd is not None:
weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')
tf.add_to_collection('losses', weight_decay)
return var
def distorted_inputs():
"""Construct distorted input for CIFAR training using the Reader ops.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
images, labels = cifar10_input.distorted_inputs(data_dir=data_dir,
batch_size=FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
def inputs(eval_data):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
images, labels = cifar10_input.inputs(eval_data=eval_data,
data_dir=data_dir,
batch_size=FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
def inference(images):
"""Build the CIFAR-10 model.
Args:
images: Images returned from distorted_inputs() or inputs().
Returns:
Logits.
"""
# We instantiate all variables using tf.get_variable() instead of
# tf.Variable() in order to share variables across multiple GPU training runs.
# If we only ran this model on a single GPU, we could simplify this function
# by replacing all instances of tf.get_variable() with tf.Variable().
#
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 1, 128],
stddev=5e-2,
wd=0.0)
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [128], tf.constant_initializer(0.0))
pre_activation = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv1)
# pool1
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
padding='SAME', name='pool1')
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm1')
# conv2
with tf.variable_scope('conv2') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 128, 128],
stddev=5e-2,
wd=0.0)
conv = tf.nn.conv2d(norm1, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [128], tf.constant_initializer(0.1))
pre_activation = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv2)
# pool2
pool2 = tf.nn.max_pool(conv2, ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1], padding='SAME', name='pool2')
norm2 = tf.nn.lrn(pool2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm1')
# conv2
with tf.variable_scope('conv3') as scope:
kernel = _variable_with_weight_decay('weights',
shape=[5, 5, 128, 128],
stddev=5e-2,
wd=0.0)
conv = tf.nn.conv2d(norm2, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [128], tf.constant_initializer(0.1))
pre_activation = tf.nn.bias_add(conv, biases)
conv3 = tf.nn.relu(pre_activation, name=scope.name)
_activation_summary(conv3)
# pool2
pool3 = tf.nn.max_pool(conv3, ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1], padding='SAME', name='pool2')
norm3 = tf.nn.lrn(pool3, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm3')
# local3
with tf.variable_scope('local3') as scope:
# Move everything into depth so we can perform a single matrix multiply.
reshape = tf.reshape(norm3, [FLAGS.batch_size, -1])
dim = reshape.get_shape()[1].value
weights = _variable_with_weight_decay('weights', shape=[dim, 512],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [512], tf.constant_initializer(0.1))
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
_activation_summary(local3)
# linear layer(WX + b),
# We don't apply softmax here because
# tf.nn.sparse_softmax_cross_entropy_with_logits accepts the unscaled logits
# and performs the softmax internally for efficiency.
with tf.variable_scope('softmax_linear') as scope:
weights = _variable_with_weight_decay('weights', [512, NUM_CLASSES],
stddev=1/192.0, wd=0.0)
biases = _variable_on_cpu('biases', [NUM_CLASSES],
tf.constant_initializer(0.0))
print(biases)
softmax_linear = tf.add(tf.matmul(local3, weights), biases, name=scope.name)
_activation_summary(softmax_linear)
return softmax_linear
def loss(logits, labels):
"""Add L2Loss to all the trainable variables.
Add summary for "Loss" and "Loss/avg".
Args:
logits: Logits from inference().
labels: Labels from distorted_inputs or inputs(). 1-D tensor
of shape [batch_size]
Returns:
Loss tensor of type float.
"""
# Calculate the average cross entropy loss across the batch.
labels = tf.cast(labels, tf.int64)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=labels, logits=logits, name='cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
# The total loss is defined as the cross entropy loss plus all of the weight
# decay terms (L2 loss).
return tf.add_n(tf.get_collection('losses'), name='total_loss')
def _add_loss_summaries(total_loss):
"""Add summaries for losses in CIFAR-10 model.
Generates moving average for all losses and associated summaries for
visualizing the performance of the network.
Args:
total_loss: Total loss from loss().
Returns:
loss_averages_op: op for generating moving averages of losses.
"""
# Compute the moving average of all individual losses and the total loss.
loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
losses = tf.get_collection('losses')
loss_averages_op = loss_averages.apply(losses + [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]:
# Name each loss as '(raw)' and name the moving average version of the loss
# as the original loss name.
tf.summary.scalar(l.op.name + ' (raw)', l)
tf.summary.scalar(l.op.name, loss_averages.average(l))
return loss_averages_op
def train(total_loss, global_step):
"""Train CIFAR-10 model.
Create an optimizer and apply to all trainable variables. Add moving
average for all trainable variables.
Args:
total_loss: Total loss from loss().
global_step: Integer Variable counting the number of training steps
processed.
Returns:
train_op: op for training.
"""
# Variables that affect learning rate.
num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size
decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY)
# Decay the learning rate exponentially based on the number of steps.
lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE,
global_step,
decay_steps,
LEARNING_RATE_DECAY_FACTOR,
staircase=True)
tf.summary.scalar('learning_rate', lr)
# Generate moving averages of all losses and associated summaries.
loss_averages_op = _add_loss_summaries(total_loss)
# Compute gradients.
with tf.control_dependencies([loss_averages_op]):
opt = tf.train.GradientDescentOptimizer(lr)
grads = opt.compute_gradients(total_loss)
# Apply gradients.
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
# Add histograms for trainable variables.
for var in tf.trainable_variables():
tf.summary.histogram(var.op.name, var)
# Add histograms for gradients.
for grad, var in grads:
if grad is not None:
tf.summary.histogram(var.op.name + '/gradients', grad)
# Track the moving averages of all trainable variables.
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
with tf.control_dependencies([apply_gradient_op, variables_averages_op]):
train_op = tf.no_op(name='train')
return train_op
def maybe_download_and_extract():
"""Download and extract the tarball from Alex's website."""
dest_directory = FLAGS.data_dir
if not os.path.exists(dest_directory):
os.makedirs(dest_directory)
filename = DATA_URL.split('/')[-1]
filepath = os.path.join(dest_directory, filename)
if not os.path.exists(filepath):
def _progress(count, block_size, total_size):
sys.stdout.write('\r>> Downloading %s %.1f%%' % (filename,
float(count * block_size) / float(total_size) * 100.0))
sys.stdout.flush()
filepath, _ = urllib.request.urlretrieve(DATA_URL, filepath, _progress)
print()
statinfo = os.stat(filepath)
print('Successfully downloaded', filename, statinfo.st_size, 'bytes.')
extracted_dir_path = os.path.join(dest_directory, 'cifar-10-batches-bin')
if not os.path.exists(extracted_dir_path):
tarfile.open(filepath, 'r:gz').extractall(dest_directory)
file cifar10_input.py：
"""Routine for decoding the CIFAR-10 binary file format."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
# Process images of this size. Note that this differs from the original CIFAR
# image size of 32 x 32. If one alters this number, then the entire model
# architecture will change and any model would need to be retrained.
IMAGE_SIZE = 24
channel = 1
# Global constants describing the CIFAR-10 data set.
NUM_CLASSES = 2
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 2310
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000
def read_cifar10(filename_queue):
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 24
result.width = 24
result.depth = channel
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def _generate_image_and_label_batch(image, label, min_queue_examples,
batch_size, shuffle):
# Create a queue that shuffles the examples, and then
# read 'batch_size' images + labels from the example queue.
num_preprocess_threads = 16
if shuffle:
images, label_batch = tf.train.shuffle_batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + channel * batch_size,
min_after_dequeue=min_queue_examples)
else:
images, label_batch = tf.train.batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + channel * batch_size)
# Display the training images in the visualizer.
tf.summary.image('images', images)
return images, tf.reshape(label_batch, [batch_size])
def distorted_inputs(data_dir, batch_size):
filenames = ['captain_nn_train.bin']
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for training the network. Note the many random
# distortions applied to the image.
# Randomly crop a [height, width] section of the image.
distorted_image = tf.random_crop(reshaped_image, [height, width, channel])
# Randomly flip the image horizontally.
distorted_image = tf.image.random_flip_left_right(distorted_image)
# Because these operations are not commutative, consider randomizing
# the order their operation.
# NOTE: since per_image_standardization zeros the mean and makes
# the stddev unit, this likely has no effect see tensorflow#1458.
distorted_image = tf.image.random_brightness(distorted_image,
max_delta=63)
distorted_image = tf.image.random_contrast(distorted_image,
lower=0.2, upper=1.8)
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_standardization(distorted_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, channel])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
min_fraction_of_examples_in_queue)
print ('Filling queue with %d CIFAR images before starting to train. '
'This will take a few minutes.' % min_queue_examples)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=True)
def inputs(eval_data, data_dir, batch_size):
if not eval_data:
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
else:
filenames = [os.path.join(data_dir, 'test_batch.bin')]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for evaluation.
# Crop the central [height, width] of the image.
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
height, width)
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_standardization(resized_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(num_examples_per_epoch *
min_fraction_of_examples_in_queue)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=False)
有人可以告诉我问题是什么以及如何修改代码来解决问题？