当我运行以下行时：
_, loss_value = sess.run([train_op, loss])
Python停止工作，但是当我运行另一个示例（如下所示）时，Python和Tensorflow不会引发任何错误。
我曾尝试将generation更改为1，并将batch_size更改为1，但这都不起作用。
这是我的（Python）代码：
# More Advanced CNN Model: CIFAR-10
#---------------------------------------
#
# In this example, we will download the CIFAR-10 images
# and build a CNN model with dropout and regularization
#
# CIFAR is composed ot 50k train and 10k test
# images that are 32x32.
import os
import sys
import tarfile
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from six.moves import urllib
from tensorflow.python.framework import ops
ops.reset_default_graph()
# Change Directory
abspath = os.path.abspath(__file__)
dname = os.path.dirname(abspath)
os.chdir(dname)
# Start a graph session
sess = tf.Session()
# Set model parameters
batch_size = 128
data_dir = 'temp'
output_every = 50
generations = 20000
eval_every = 500
image_height = 32
image_width = 32
crop_height = 24
crop_width = 24
num_channels = 3
num_targets = 10
extract_folder = 'cifar-10-batches-bin'
# Exponential Learning Rate Decay Params
learning_rate = 0.1
lr_decay = 0.1
num_gens_to_wait = 250.
# Extract model parameters
image_vec_length = image_height * image_width * num_channels
record_length = 1 + image_vec_length # ( + 1 for the 0-9 label)
# Load data
data_dir = 'temp'
if not os.path.exists(data_dir):
os.makedirs(data_dir)
cifar10_url = 'http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz'
# Check if file exists, otherwise download it
data_file = os.path.join(data_dir, 'cifar-10-binary.tar.gz')
if os.path.isfile(data_file):
pass
else:
# Download file
def progress(block_num, block_size, total_size):
progress_info = [cifar10_url, float(block_num * block_size) / float(total_size) * 100.0]
print('\r Downloading {} - {:.2f}%'.format(*progress_info), end="")
filepath, _ = urllib.request.urlretrieve(cifar10_url, data_file, progress)
# Extract file
tarfile.open(filepath, 'r:gz').extractall(data_dir)
# Define CIFAR reader
def read_cifar_files(filename_queue, distort_images = True):
reader = tf.FixedLengthRecordReader(record_bytes=record_length)
key, record_string = reader.read(filename_queue)
record_bytes = tf.decode_raw(record_string, tf.uint8)
image_label = tf.cast(tf.slice(record_bytes, [0], [1]), tf.int32)
# Extract image
image_extracted = tf.reshape(tf.slice(record_bytes, [1], [image_vec_length]),
[num_channels, image_height, image_width])
# Reshape image
image_uint8image = tf.transpose(image_extracted, [1, 2, 0])
reshaped_image = tf.cast(image_uint8image, tf.float32)
# Randomly Crop image
final_image = tf.image.resize_image_with_crop_or_pad(reshaped_image, crop_width, crop_height)
if distort_images:
# Randomly flip the image horizontally, change the brightness and contrast
final_image = tf.image.random_flip_left_right(final_image)
final_image = tf.image.random_brightness(final_image,max_delta=63)
final_image = tf.image.random_contrast(final_image,lower=0.2, upper=1.8)
# Normalize whitening
final_image = tf.image.per_image_whitening(final_image)
return(final_image, image_label)
# Create a CIFAR image pipeline from reader
def input_pipeline(batch_size, train_logical=True):
if train_logical:
files = [os.path.join(data_dir, extract_folder, 'data_batch_{}.bin'.format(i)) for i in range(1,6)]
else:
files = [os.path.join(data_dir, extract_folder, 'test_batch.bin')]
filename_queue = tf.train.string_input_producer(files)
image, label = read_cifar_files(filename_queue)
# min_after_dequeue defines how big a buffer we will randomly sample
# from -- bigger means better shuffling but slower start up and more
# memory used.
# capacity must be larger than min_after_dequeue and the amount larger
# determines the maximum we will prefetch. Recommendation:
# min_after_dequeue + (num_threads + a small safety margin) * batch_size
min_after_dequeue = 5000
capacity = min_after_dequeue + 3 * batch_size
example_batch, label_batch = tf.train.shuffle_batch([image, label],
batch_size=batch_size,
capacity=capacity,
min_after_dequeue=min_after_dequeue)
return(example_batch, label_batch)
# Define the model architecture, this will return logits from images
def cifar_cnn_model(input_images, batch_size, train_logical=True):
def truncated_normal_var(name, shape, dtype):
return(tf.get_variable(name=name, shape=shape, dtype=dtype, initializer=tf.truncated_normal_initializer(stddev=0.05)))
def zero_var(name, shape, dtype):
return(tf.get_variable(name=name, shape=shape, dtype=dtype, initializer=tf.constant_initializer(0.0)))
# First Convolutional Layer
with tf.variable_scope('conv1') as scope:
# Conv_kernel is 5x5 for all 3 colors and we will create 64 features
conv1_kernel = truncated_normal_var(name='conv_kernel1', shape=[5, 5, 3, 64], dtype=tf.float32)
# We convolve across the image with a stride size of 1
conv1 = tf.nn.conv2d(input_images, conv1_kernel, [1, 1, 1, 1], padding='SAME')
# Initialize and add the bias term
conv1_bias = zero_var(name='conv_bias1', shape=[64], dtype=tf.float32)
conv1_add_bias = tf.nn.bias_add(conv1, conv1_bias)
# ReLU element wise
relu_conv1 = tf.nn.relu(conv1_add_bias)
# Max Pooling
pool1 = tf.nn.max_pool(relu_conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],padding='SAME', name='pool_layer1')
# Local Response Normalization (parameters from paper)
# paper: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks
norm1 = tf.nn.lrn(pool1, depth_radius=5, bias=2.0, alpha=1e-3, beta=0.75, name='norm1')
# Second Convolutional Layer
with tf.variable_scope('conv2') as scope:
# Conv kernel is 5x5, across all prior 64 features and we create 64 more features
conv2_kernel = truncated_normal_var(name='conv_kernel2', shape=[5, 5, 64, 64], dtype=tf.float32)
# Convolve filter across prior output with stride size of 1
conv2 = tf.nn.conv2d(norm1, conv2_kernel, [1, 1, 1, 1], padding='SAME')
# Initialize and add the bias
conv2_bias = zero_var(name='conv_bias2', shape=[64], dtype=tf.float32)
conv2_add_bias = tf.nn.bias_add(conv2, conv2_bias)
# ReLU element wise
relu_conv2 = tf.nn.relu(conv2_add_bias)
# Max Pooling
pool2 = tf.nn.max_pool(relu_conv2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name='pool_layer2')
# Local Response Normalization (parameters from paper)
norm2 = tf.nn.lrn(pool2, depth_radius=5, bias=2.0, alpha=1e-3, beta=0.75, name='norm2')
# Reshape output into a single matrix for multiplication for the fully connected layers
reshaped_output = tf.reshape(norm2, [batch_size, -1])
reshaped_dim = reshaped_output.get_shape()[1].value
# First Fully Connected Layer
with tf.variable_scope('full1') as scope:
# Fully connected layer will have 384 outputs.
full_weight1 = truncated_normal_var(name='full_mult1', shape=[reshaped_dim, 384], dtype=tf.float32)
full_bias1 = zero_var(name='full_bias1', shape=[384], dtype=tf.float32)
full_layer1 = tf.nn.relu(tf.add(tf.matmul(reshaped_output, full_weight1), full_bias1))
# Second Fully Connected Layer
with tf.variable_scope('full2') as scope:
# Second fully connected layer has 192 outputs.
full_weight2 = truncated_normal_var(name='full_mult2', shape=[384, 192], dtype=tf.float32)
full_bias2 = zero_var(name='full_bias2', shape=[192], dtype=tf.float32)
full_layer2 = tf.nn.relu(tf.add(tf.matmul(full_layer1, full_weight2), full_bias2))
# Final Fully Connected Layer -> 10 categories for output (num_targets)
with tf.variable_scope('full3') as scope:
# Final fully connected layer has 10 (num_targets) outputs.
full_weight3 = truncated_normal_var(name='full_mult3', shape=[192, num_targets], dtype=tf.float32)
full_bias3 = zero_var(name='full_bias3', shape=[num_targets], dtype=tf.float32)
final_output = tf.add(tf.matmul(full_layer2, full_weight3), full_bias3)
return(final_output)
# Loss function
def cifar_loss(logits, targets):
# Get rid of extra dimensions and cast targets into integers
targets = tf.squeeze(tf.cast(targets, tf.int32))
# Calculate cross entropy from logits and targets
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits, targets)
# Take the average loss across batch size
cross_entropy_mean = tf.reduce_mean(cross_entropy, name='cross_entropy')
return(cross_entropy_mean)
# Train step
def train_step(loss_value, generation_num):
# Our learning rate is an exponential decay after we wait a fair number of generations
model_learning_rate = tf.train.exponential_decay(learning_rate, generation_num,
num_gens_to_wait, lr_decay, staircase=True)
# Create optimizer
my_optimizer = tf.train.GradientDescentOptimizer(model_learning_rate)
# Initialize train step
train_step = my_optimizer.minimize(loss_value)
return(train_step)
# Accuracy function
def accuracy_of_batch(logits, targets):
# Make sure targets are integers and drop extra dimensions
targets = tf.squeeze(tf.cast(targets, tf.int32))
# Get predicted values by finding which logit is the greatest
batch_predictions = tf.cast(tf.argmax(logits, 1), tf.int32)
# Check if they are equal across the batch
predicted_correctly = tf.equal(batch_predictions, targets)
# Average the 1's and 0's (True's and False's) across the batch size
accuracy = tf.reduce_mean(tf.cast(predicted_correctly, tf.float32))
return(accuracy)
# Get data
print('Getting/Transforming Data.')
# Initialize the data pipeline
images, targets = input_pipeline(batch_size, train_logical=True)
# Get batch test images and targets from pipline
test_images, test_targets = input_pipeline(batch_size, train_logical=False)
# Declare Model
print('Creating the CIFAR10 Model.')
with tf.variable_scope('model_definition') as scope:
# Declare the training network model
model_output = cifar_cnn_model(images, batch_size)
# This is very important!!! We must set the scope to REUSE the variables,
# otherwise, when we set the test network model, it will create new random
# variables. Otherwise we get random evaluations on the test batches.
scope.reuse_variables()
test_output = cifar_cnn_model(test_images, batch_size)
# Declare loss function
print('Declare Loss Function.')
loss = cifar_loss(model_output, targets)
# Create accuracy function
accuracy = accuracy_of_batch(test_output, test_targets)
# Create training operations
print('Creating the Training Operation.')
generation_num = tf.Variable(0, trainable=False)
train_op = train_step(loss, generation_num)
# Initialize Variables
print('Initializing the Variables.')
init = tf.initialize_all_variables()
sess.run(init)
# Initialize queue (This queue will feed into the model, so no placeholders necessary)
tf.train.start_queue_runners(sess=sess)
# Train CIFAR Model
print('Starting Training')
train_loss = []
test_accuracy = []
for i in range(generations):
_, loss_value = sess.run([train_op, loss])
if (i+1) % output_every == 0:
train_loss.append(loss_value)
output = 'Generation {}: Loss = {:.5f}'.format((i+1), loss_value)
print(output)
if (i+1) % eval_every == 0:
[temp_accuracy] = sess.run([accuracy])
test_accuracy.append(temp_accuracy)
acc_output = ' --- Test Accuracy = {:.2f}%.'.format(100.*temp_accuracy)
print(acc_output)
# Print loss and accuracy
# Matlotlib code to plot the loss and accuracies
eval_indices = range(0, generations, eval_every)
output_indices = range(0, generations, output_every)
# Plot loss over time
plt.plot(output_indices, train_loss, 'k-')
plt.title('Softmax Loss per Generation')
plt.xlabel('Generation')
plt.ylabel('Softmax Loss')
plt.show()
# Plot accuracy over time
plt.plot(eval_indices, test_accuracy, 'k-')
plt.title('Test Accuracy')
plt.xlabel('Generation')
plt.ylabel('Accuracy')
plt.show()
这是错误日志：
2019-05-07 15:26:48.809018: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2019-05-07 15:26:49.083235: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties:
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.873
pciBusID: 0000:01:00.0
totalMemory: 8.00GiB freeMemory: 6.59GiB
2019-05-07 15:26:49.090110: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0
2019-05-07 15:26:49.872151: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-05-07 15:26:49.876033: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988] 0
2019-05-07 15:26:49.878186: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0: N
2019-05-07 15:26:49.880459: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6353 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
WARNING:tensorflow:From 8.3-cnn_cifar10.py:88: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From F:\study\machinelearning\ENV\lib\site-packages\tensorflow\python\training\input.py:276: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From F:\study\machinelearning\ENV\lib\site-packages\tensorflow\python\training\input.py:188: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensors(tensor).repeat(num_epochs)`.
WARNING:tensorflow:From F:\study\machinelearning\ENV\lib\site-packages\tensorflow\python\training\input.py:197: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From F:\study\machinelearning\ENV\lib\site-packages\tensorflow\python\training\input.py:197: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From 8.3-cnn_cifar10.py:59: FixedLengthRecordReader.__init__ (from tensorflow.python.ops.io_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.FixedLengthRecordDataset`.
WARNING:tensorflow:From 8.3-cnn_cifar10.py:93: shuffle_batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.shuffle(min_after_dequeue).batch(batch_size)`.
Tensor("shuffle_batch:0", shape=(32, 24, 24, 3), dtype=float32)
cifar_loss---------------------0
cifar_loss---------------------1
train_step--------------------------0
train_step--------------------------1
train_step--------------------------2
train_step--------------------------3
WARNING:tensorflow:From 8.3-cnn_cifar10.py:195: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
信息：我当前正在使用Windows 10（x64），Tensorflow 1.12，Python 3和cudn-9.0
答案 0 :(得分：0)
该示例可能是为TensorFlow的旧版本编写的。尝试降级为TF 1.9。
答案 1 :(得分：0)
我将读取数据的代码替换为以下代码：
def _get_images_labels(batch_size, split, distords=False):
"""Returns Dataset for given split."""
dataset = tfds.load(name='cifar10', split=split)
print("load successed.")
print(dataset)
scope = 'data_augmentation' if distords else 'input'
with tf.name_scope(scope):
dataset = dataset.map(DataPreprocessor(distords), num_parallel_calls=10)
# Dataset is small enough to be fully loaded on memory:
dataset = dataset.prefetch(-1)
dataset = dataset.repeat().batch(batch_size)
iterator = dataset.make_one_shot_iterator()
images_labels = iterator.get_next()
images, labels = images_labels['input'], images_labels['target']
tf.summary.image('images', images)
return images, labels
class DataPreprocessor(object):
"""Applies transformations to dataset record."""
def __init__(self, distords):
self._distords = distords
def __call__(self, record):
"""Process img for training or eval."""
img = record['image']
img = tf.cast(img, tf.float32)
if self._distords: # training
# Randomly crop a [height, width] section of the image.
img = tf.random_crop(img, [image_width, image_height, 3])
# Randomly flip the image horizontally.
img = tf.image.random_flip_left_right(img)
# 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.
img = tf.image.random_brightness(img, max_delta=63)
img = tf.image.random_contrast(img, lower=0.2, upper=1.8)
else: # Image processing for evaluation.
# Crop the central [height, width] of the image.
img = tf.image.resize_image_with_crop_or_pad(img, image_width, image_height)
# Subtract off the mean and divide by the variance of the pixels.
img = tf.image.per_image_standardization(img)
return dict(input=img, target=record['label'])
然后问题解决了。希望它对其他人有用。谢谢〜