2

tf.nn.conv2d_transpose我在正常工作方面遇到了问题。这是我正在尝试做的一个小复制：

import tensorflow as tf
import numpy as np

# Shape (2, 3, 3, 1) == (batch_sz, height, width, channels)
inp = tf.Variable(np.array(
    [
        [
            [[1], [2], [3]],
            [[2], [3], [4]],
            [[7], [8], [9]]
        ],
        [
            [[3], [2], [1]],
            [[2], [7], [2]],
            [[3], [2], [0]]
        ]
    ], dtype = np.float32
))
# Shape (5, 5, 3, 1) == (kH, kW, out_channels, in_channels)
ker = tf.Variable(np.array(
    [
        [[[1],[2],[1]], [[2],[2],[2]], [[1],[2],[1]], [[2],[1],[1]], [[1],[1],[1]]],
        [[[1],[2],[1]], [[2],[2],[2]], [[1],[2],[1]], [[2],[1],[1]], [[1],[1],[1]]],
        [[[1],[2],[1]], [[2],[2],[2]], [[1],[2],[1]], [[2],[1],[1]], [[1],[1],[1]]],
        [[[1],[2],[1]], [[2],[2],[2]], [[1],[2],[1]], [[2],[1],[1]], [[1],[1],[1]]],
        [[[1],[2],[1]], [[2],[2],[2]], [[1],[2],[1]], [[2],[1],[1]], [[1],[1],[1]]]
    ], dtype = np.float32
))
out = tf.nn.conv2d_transpose(inp, ker, (2, 7, 7, 1), (1, 1, 1, 1), padding='SAME', data_format='NHWC', name='conv_transpose')

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    output, kernel, input = sess.run([out, ker, inp])

我想要的是使用三个 5x5x1 过滤器对 3x3x1 输入执行转置卷积。我希望输出的形状为 7x7x3 - 但相反，我收到一条错误消息：

InvalidArgumentError: Conv2DCustomBackpropInput: input and filter must have the same depth
     [[Node: conv_transpose_2 = Conv2DBackpropInput[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](conv_transpose_2/output_shape, Variable_21/read, Variable_20/read)]]

输入和过滤器深度不是都等于1吗？我看不出我做错了什么 - 任何提示都会非常感激。我特别想使用tf.nn.conv2d_transpose而不是tf.layers.conv2d_transpose.

4

1 回答 1

0

此问题类似于此Stack Overflow 问题。

您应该进行以下更改以使您的代码运行。

  1. 的形状inp应该是 (2, 3, 3, 3) 而不是 (2, 3, 3, 1)
  2. 的形状ker应该是 (5,5,1,3) 而不是 (5,5,3,1)
  3. 填充应设置为 'VALID' 而不是 'SAME' 只有这样Output Shape才会不同于Input Shape.

下面提到的是工作代码（为了便于实施，用零做了）：

import tensorflow as tf
import numpy as np

# Shape (2, 3, 3, 3) == (batch_sz, height, width, channels)
inp = tf.Variable(np.array(np.zeros((2, 3, 3, 3)) , dtype = np.float32))

# Shape (5, 5, 3, 1) == (kH, kW, out_channels, in_channels)
ker = tf.Variable(np.zeros((5,5,1,3)) , dtype = np.float32)

out = tf.nn.conv2d_transpose(value = inp, filter = ker, output_shape=(2, 7, 7, 1), 
                             strides=(1, 1, 1, 1), padding='VALID', data_format='NHWC', name='conv_transpose')

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    output, kernel, input = sess.run([out, ker, inp])
于 2019-11-12T10:51:34.763 回答