我遇到了这个错误，我无法弄清楚原因。如果有人能帮忙会很棒。 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)
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)]]
看起来这个问题出现在convolutional_neural_network layer（）函数中，其中不知何故它无法将矩阵的相同维度相乘。但目前尚不清楚如何解决这个问题 感谢您提前获得帮助......
答案 0 :(得分：1)
在第conv4行重塑fc1 = tf.reshape(conv4,[256,-1])后，fc1的形状为(256, 2048)，权重矩阵W_fc1的形状为(256, 1024)。因此，在矩阵乘法部分的下一行fc1 = tf.nn.relu(tf.matmul(fc1, weights['W_fc1']) + biases['b_fc1'])
处会出现大小不兼容的错误。我建议你手动完成每一步的维度，以便在将来找到错误。