当我调用“sess.run()”时，“python.exe”程序引发错误

Posted 2023-02-19

【中文标题】当我调用“sess.run()”时，“python.exe”程序引发错误

【英文标题】：The "python.exe" program raises an error when I call "sess.run()"

【发布时间】：2019-09-24 19:38:18

【问题描述】：

当我运行以下行时：

_, loss_value = sess.run([train_op, loss])

Python 停止工作，但当我运行另一个示例（如下）时，Python 和 Tensorflow 不会引发任何错误。

我尝试将generation 更改为1，并将batch_size 更改为1，但这也没有用。

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：我目前使用的是 Windows 10 (x64)、Tensorflow 1.12、Python 3 和 cudn-9.0

【问题讨论】：

您好，可以打印出您的错误信息吗？

我把日志加到最后。谢谢@sslloo

我没有看到任何错误，只是一堆弃用警告。

是的，但是python已经停止工作了。@xdurch0

【参考方案1】：

该示例可能是为旧版本的 TensorFlow 编写的。尝试降级到 TF 1.9。

【讨论】：

是的，旧版本的 tensorflow 的代码是 weitten。但我想在新版本中使用它。其他示例都可以。日志只显示警告，所以我想得到一些新版本解决问题的小技巧

【参考方案2】：

我把读取数据的代码替换成下面的代码：

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'])

然后问题就解决了。希望对其他人有用。谢谢~