tensorflow - InvalidArgumentError : Matrix size-incompatible: In[0]: [256, 2048], In[1] : [256, 1024]

Question

我一直收到这个错误，我无法弄清楚原因。如果有人可以提供帮助，那就太好了。
这是我的代码:

import numpy as np
import pickle
import os
import download
#from dataset import one_hot_encoded
#from sklearn.preprocessing import OneHotEncoder
import tensorflow as tf
from random import shuffle

data_path = "D:/Personal details/Internship/"

# Width and height of each image.
img_size = 32

# Number of channels in each image, 3 channels: Red, Green, Blue.
num_channels = 3

# Length of an image when flattened to a 1-dim array.
img_size_flat = img_size * img_size * num_channels

# Number of classes.
num_classes = 10

# Number of files for the training-set.
_num_files_train = 5

# Number of images for each batch-file in the training-set.
_images_per_file = 10000

def _get_file_path(filename=""):

    return os.path.join(data_path, "cifar-10-batches-py/", filename)


def _unpickle(filename):

    file_path = _get_file_path(filename)

    print("Loading data: " + file_path)

    with open(file_path, mode='rb') as file:
        # In Python 3.X it is important to set the encoding,
        # otherwise an exception is raised here.
        data = pickle.load(file, encoding='bytes')

    return data


def _convert_images(raw):

    # Convert the raw images from the data-files to floating-points.
    raw_float = np.array(raw, dtype=float) / 255.0

    # Reshape the array to 4-dimensions.
    images = raw_float.reshape([-1, num_channels, img_size, img_size])

    # Reorder the indices of the array.
    images = images.transpose([0, 2, 3, 1])

    return images


def _load_data(filename):

    # Load the pickled data-file.
    data = _unpickle(filename)

    # Get the raw images.
    raw_images = data[b'data']

    # Get the class-numbers for each image. Convert to numpy-array.
    cls = np.array(data[b'labels'])

    # Convert the images.
    images = _convert_images(raw_images)

    return images, cls


def load_class_names():

    # Load the class-names from the pickled file.
    raw = _unpickle(filename="batches.meta")[b'label_names']

    # Convert from binary strings.
    names = [x.decode('utf-8') for x in raw]

    return names


def load_training_data():

    images = np.zeros(shape=[_num_images_train, img_size, img_size, num_channels], dtype=float)
    cls = np.zeros(shape=[_num_images_train], dtype=int)

    # Begin-index for the current batch.
    begin = 0

    # For each data-file.
    for i in range(_num_files_train):
        # Load the images and class-numbers from the data-file.
        images_batch, cls_batch = _load_data(filename="data_batch_" + str(i + 1))

        # Number of images in this batch.
        num_images = len(images_batch)

        # End-index for the current batch.
        end = begin + num_images

        # Store the images into the array.
        images[begin:end, :] = images_batch

        # Store the class-numbers into the array.
        cls[begin:end] = cls_batch

        # The begin-index for the next batch is the current end-index.
        begin = end

    return images, cls, one_hot_encoded(class_numbers=cls, num_classes=num_classes)


def load_test_data():

    images, cls = _load_data(filename="test_batch")

    return images, cls, one_hot_encoded(class_numbers=cls, num_classes=num_classes)

########################################################################

def one_hot_encoded(class_numbers, num_classes=None):

    if num_classes is None:
        num_classes = np.max(class_numbers) + 1

    return np.eye(num_classes, dtype=float)[class_numbers]


class_names = load_class_names()
images_train, cls_train, labels_train = load_training_data()
images_test, cls_test, labels_test = load_test_data()

images_train_train = images_train[0:45000]
validation_train = images_train[45000:50000]
labels_train_train = labels_train[0:45000]
validation_labels = labels_train[45000:]


print(len(images_train_train))
print(len(validation_train))
##print(class_names)
##print(len(images_train))
##print(cls_train)
##print(labels_train)
##print(cls_test)
##print(labels_test)

n_classes = len(class_names)
batch_size = 128

x = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name='x')
y = tf.placeholder(tf.float32, shape=[None, n_classes], name='y_true')

def conv2d(x,W):
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
def maxpool2d(x):
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

def convolutional_neural_network(x):
    weights = {'W_conv1': tf.Variable(tf.random_normal([3,3,3,64])),
               'W_conv2': tf.Variable(tf.random_normal([3,3,64,128])),
               'W_conv3': tf.Variable(tf.random_normal([3,3,128,256])),
               'W_conv4': tf.Variable(tf.random_normal([3,3,256,256])),
               'W_fc1': tf.Variable(tf.random_normal([256,1024])),
               'W_fc2': tf.Variable(tf.random_normal([1024,1024])),
               'soft_max': tf.Variable(tf.random_normal([1024, n_classes]))}

    biases = {'b_conv1': tf.Variable(tf.random_normal([64])),
               'b_conv2': tf.Variable(tf.random_normal([128])),
               'b_conv3': tf.Variable(tf.random_normal([256])),
               'b_conv4': tf.Variable(tf.random_normal([256])),
               'b_fc1': tf.Variable(tf.random_normal([1024])),
               'b_fc2': tf.Variable(tf.random_normal([1024])),
               'soft_max': tf.Variable(tf.random_normal([n_classes]))}

    conv1 = tf.nn.relu(conv2d(x, weights['W_conv1']) + biases['b_conv1'])
    conv1 = maxpool2d(conv1)

    conv2 = tf.nn.relu(conv2d(conv1, weights['W_conv2']) + biases['b_conv2'])
    conv2 = maxpool2d(conv2)

    conv3 = tf.nn.relu(conv2d(conv2, weights['W_conv3']) + biases['b_conv3'])

    conv4 = tf.nn.relu(conv2d(conv3, weights['W_conv4']) + biases['b_conv4'])
    conv4 = maxpool2d(conv4)

    fc1 = tf.reshape(conv4,[256,-1])
    fc1 = tf.nn.relu(tf.matmul(fc1, weights['W_fc1']) + biases['b_fc1'])

    fc2 = tf.nn.relu(tf.matmul(fc1, weights['W_fc2'] + biases['b_fc2']))

    soft_max = tf.matmul(fc2, weights['soft_max']) + biases['soft_max']

    return soft_max

def train_neural_network(x):
    prediction = convolutional_neural_network(x)
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits = prediction,labels = y) )
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 3
    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())

        for epoch in range(hm_epochs):
            epoch_loss = 0

            i = 0
            while i < len(images_train_train):
                start = i
                end = i+batch_size

                batch_x = np.array(images_train_train[start:end])
                batch_y = np.array(labels_train_train[start:end])
                _, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
                epoch_loss += c

            print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)

        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))

        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy:',accuracy.eval({x:validation_train, y:validation_labels}))

train_neural_network(x)

Ans 这是我遇到的错误。

WARNING:tensorflow:From D:/Personal details/Internship/cifar-10v1.0.py:310: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See @{tf.nn.softmax_cross_entropy_with_logits_v2}.

WARNING:tensorflow:From C:\Python35\lib\site-packages\tensorflow\python\util\tf_should_use.py:118: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
Traceback (most recent call last):
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1322, in _do_call
    return fn(*args)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1307, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1409, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix size-incompatible: In[0]: [256,2048], In[1]: [256,1024]
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Reshape, Variable_4/read)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:/Personal details/Internship/cifar-10v1.0.py", line 344, in <module>
    train_neural_network(x)
  File "D:/Personal details/Internship/cifar-10v1.0.py", line 327, in train_neural_network
    _, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 900, in run
    run_metadata_ptr)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1135, in _run
    feed_dict_tensor, options, run_metadata)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1316, in _do_run
    run_metadata)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1335, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix size-incompatible: In[0]: [256,2048], In[1]: [256,1024]
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Reshape, Variable_4/read)]]

Caused by op 'MatMul', defined at:
  File "<string>", line 1, in <module>
  File "C:\Python35\lib\idlelib\run.py", line 130, in main
    ret = method(*args, **kwargs)
  File "C:\Python35\lib\idlelib\run.py", line 357, in runcode
    exec(code, self.locals)
  File "D:/Personal details/Internship/cifar-10v1.0.py", line 344, in <module>
    train_neural_network(x)
  File "D:/Personal details/Internship/cifar-10v1.0.py", line 309, in train_neural_network
    prediction = convolutional_neural_network(x)
  File "D:/Personal details/Internship/cifar-10v1.0.py", line 300, in convolutional_neural_network
    fc1 = tf.nn.relu(tf.matmul(fc1, weights['W_fc1']) + biases['b_fc1'])
  File "C:\Python35\lib\site-packages\tensorflow\python\ops\math_ops.py", line 2122, in matmul
    a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 4567, in mat_mul
    name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
    op_def=op_def)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1718, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Matrix size-incompatible: In[0]: [256,2048], In[1]: [256,1024]
     [[Node: MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Reshape, Variable_4/read)]]

看起来问题出在卷积神经网络层()函数中，其中以某种方式无法乘以矩阵的相同维度而生气。但不清楚如何解决问题
提前感谢您的帮助...

Answer 1

整形后conv4在线 fc1 = tf.reshape(conv4,[256,-1]) ，形状fc1是 (256, 2048)和权重矩阵 W_fc1有形状(256, 1024) .因此，您会在下一行 fc1 = tf.nn.relu(tf.matmul(fc1, weights['W_fc1']) + biases['b_fc1'])
处收到大小不兼容的错误。在矩阵乘法部分。我建议您手动检查每一步的尺寸，以便将来查找错误。