输入通道与过滤器的输入通道不匹配（Tensorflow）

Question

我想使用 tf.nn.conv2d_transpose 为 GAN 网络构建反卷积层。

我想创建一个函数 deconv_layer。它生成一个新层，输出 filter_num 过滤器，其分辨率是输入分辨率的 expand_size 倍。

我的代码是：

def deconv_layer(x, filter_num, kernel_size=5, expand_size=2):

    x_shape = x.get_shape().as_list()

    with tf.name_scope('deconv_'+str(filter_num)):

        size_in = x_shape[-1]
        size_out = filter_num

        w = tf.Variable(tf.random_normal([kernel_size, kernel_size, size_in, size_out], mean=0.0, stddev=0.125), name="W")
        b = tf.Variable(tf.random_normal([size_out], mean=0.0, stddev=0.125), name="B")

        conv = tf.nn.conv2d_transpose(x, w, output_shape=[-1, x_shape[-3]*expand_size, x_shape[-2]*expand_size, filter_num], strides=[1,expand_size,expand_size,1], padding="SAME")
        act = tf.nn.relu(tf.nn.bias_add(conv, b))

        tf.summary.histogram('weights', w)
        tf.summary.histogram('biases', b)
        tf.summary.histogram('activations', act)

    return act

错误信息：

ValueError: input channels does not match filter's input channels
At conv = tf.nn.conv2d_transpose(...)

我不确定我是否正确使用了tf.nn.conv2d_transpose。我尝试基于卷积层创建它。

Answer 1

过滤器尺寸错误。根据 docs:

filter: A 4-D Tensor with the same type as value and shape [height, width, output_channels, in_channels]. filter's in_channels dimension must match that of value (input).

您需要将 w 尺码更改为：

w = tf.Variable(tf.random_normal([kernel_size, kernel_size, size_out, size_in], mean=0.0, stddev=0.125), name="W")

输入通道与过滤器的输入通道不匹配（Tensorflow）

input channels does not match filter's input channels (Tensorflow)

python

neural-network

conv-neural-network

tensorflow

deconvolution