尺寸必須相等，但對於輸入形狀為[？，24,24,1]，[5,5,64,64]的'Conv2D_1'（op：'Conv2D'），尺寸應為1和64

Question

我有以下代碼：

import numpy as np
import matplotlib.pyplot as plt
import cifar_tools
import tensorflow as tf

data, labels = cifar_tools.read_data('C:\\Users\\abc\\Desktop\\temp')

x = tf.placeholder(tf.float32, [None, 24 * 24])
y = tf.placeholder(tf.float32, [None, 2])

w1 = tf.Variable(tf.random_normal([5, 5, 1, 64]))
b1 = tf.Variable(tf.random_normal([64]))

w2 = tf.Variable(tf.random_normal([5, 5, 64, 64]))
b2 = tf.Variable(tf.random_normal([64]))

w3 = tf.Variable(tf.random_normal([6*6*64, 1024]))
b3 = tf.Variable(tf.random_normal([1024]))

w_out = tf.Variable(tf.random_normal([1024, 2]))
b_out = tf.Variable(tf.random_normal([2]))

def conv_layer(x,w,b):
    conv = tf.nn.conv2d(x,w,strides=[1,1,1,1], padding = 'SAME')
    conv_with_b = tf.nn.bias_add(conv,b)
    conv_out = tf.nn.relu(conv_with_b)
    return conv_out

def maxpool_layer(conv,k=2):
    return tf.nn.max_pool(conv, ksize=[1,k,k,1], strides=[1,k,k,1], padding='SAME')

def model():
    x_reshaped = tf.reshape(x, shape=[-1,24,24,1])

    conv_out1 = conv_layer(x_reshaped, w1, b1)
    maxpool_out1 = maxpool_layer(conv_out1)
    norm1 = tf.nn.lrn(maxpool_out1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)

    conv_out2 = conv_layer(x_reshaped, w2, b2)
    norm2 = tf.nn.lrn(maxpool_out2, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
    maxpool_out2 = maxpool_layer(conv_out2)

    maxpool_reshaped = tf.reshape(maxpool_out2, [-1,w3.get_shape().as_list()[0]])
    local = tf.add(tf.matmul(maxpool_reshaped, w3), b3)
    local_out = tf.nn.relu(local)

    out = tf.add(tf.matmul(local_out, w_out), b_out)
    return out

model_op = model()

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_legits(model_op, y))
train_op = tf.train.AdamOptimizer(learning_rate-0.001).minimize(cost)

current_pred = tf.equal(tf.argmax(model_op, 1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred,tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    onehot_labels = tf.one_hot(labels, 2, on_value=1.,off_value=0.,axis=-1)
    onehot_vals = sess.run(onehot_labels)
    batch_size = len(data) / 200
    print('batch size', batch_size)
    for j in range(0, 1000):
        print('EPOCH', j)
        for j in range(0, len(data), batch_size):
            batch_data = data[i:i+batch_size, :]
            batch_onehot_vals = onehot_vals[i,i+batch_size, :]
            _, accuracy_val = sess.run([train_op, accuracy], feed_dict={x: batch_data, y: batch_onehot_vals})
            if i % 1000 == 0:
                print(i, accuracy_val)
        print('DONE WITH EPOCH')

運行代碼時，出現以下錯誤，我不確定如何解決：

Traceback (most recent call last):
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 670, in _call_cpp_shape_fn_impl
    status)
  File "C:\Python35\lib\contextlib.py", line 66, in __exit__
    next(self.gen)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 469, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 1 and 64 for 'Conv2D_1' (op: 'Conv2D') with input shapes: [?,24,24,1], [5,5,64,64].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "cnn.py", line 50, in <module>
    model_op = model()
  File "cnn.py", line 39, in model
    conv_out2 = conv_layer(x_reshaped, w2, b2)
  File "cnn.py", line 24, in conv_layer
    conv = tf.nn.conv2d(x,w,strides=[1,1,1,1], padding = 'SAME')
  File "C:\Python35\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 396, in conv2d
    data_format=data_format, name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 759, in apply_op
    op_def=op_def)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 2242, in create_op
    set_shapes_for_outputs(ret)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1617, in set_shapes_for_outputs
    shapes = shape_func(op)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1568, in call_with_requiring
    return call_cpp_shape_fn(op, require_shape_fn=True)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 610, in call_cpp_shape_fn
    debug_python_shape_fn, require_shape_fn)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 675, in _call_cpp_shape_fn_impl
    raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 1 and 64 for 'Conv2D_1' (op: 'Conv2D') with input shapes: [?,24,24,1], [5,5,64,64].

您對我為什么會收到此錯誤以及如何解決它有想法嗎？

謝謝。

Answer 1

在您的代碼中，您也將第二次卷積應用於原始數據

conv_out2 = conv_layer(x_reshaped, w2, b2)

然后通道數不匹配（原始數據中的1個通道， w2 64個輸入通道）。

如果要將其應用於第一層的輸出，請將其替換為maxpool_out1 ，即：

conv_out2 = conv_layer(maxpool_out1, w2, b2)

然后通道數應該匹配，因為w1有64個輸出通道。

另外，在代碼的以下部分

conv_out2 = conv_layer(x_reshaped, w2, b2)
norm2 = tf.nn.lrn(maxpool_out2, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)
maxpool_out2 = maxpool_layer(conv_out2)

我認為您應該顛倒最后兩行的順序。 因為您在定義它之前使用了maxpool_out2 。