输入通道与滤波器的输入通道不匹配(Tensorflow)

时间:2018-05-19 11:57:56

标签: python tensorflow neural-network conv-neural-network deconvolution

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

我想创建一个函数deconv_layer。它会生成一个新图层,输出filter_num个过滤器,其输出分辨率为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

错误消息:

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tf.nn.conv2d_transpose。我试图基于卷积层创建它。

1 个答案:

答案 0 :(得分:1)

过滤器尺寸错误。根据{{​​3}}:

  

过滤器:4-D Tensor,其值与形状相同[高度,   width,output_channels,in_channels]。过滤器的in_channels维度   必须匹配值(输入)。

您需要将w尺寸更改为:

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