tflearn DCGAN中鉴别符形状的值误差

Question

我正在尝试使用tflearn框架构建与自定义数据集一起使用的DCGAN。

目前，我认为问题出在鉴别代码中，但我不确定。如果您在第二个conv_2d层中更改形状，则会更改错误消息中的第一个数字。

*ngIf=“d.type==‘image’”

失败，并显示错误代码：

def discriminator(x, reuse=False):
    with tf.variable_scope('Discriminator', reuse=reuse):
        x = tflearn.conv_2d(x, 64, 5, activation='tanh')
        x = tflearn.avg_pool_2d(x, 2)
        x = tflearn.conv_2d(x, 6272, 5, activation='tanh')
        x = tflearn.avg_pool_2d(x, 2)
        x = tflearn.fully_connected(x, 1024, activation='tanh')
        x = tflearn.fully_connected(x, 2)
        x = tf.nn.softmax(x)
        return x


# Input Data
gen_input = tflearn.input_data(shape=[None, z_dim], name='input_gen_noise')
input_disc_noise = tflearn.input_data(shape=[None, z_dim], name='input_disc_noise')
input_disc_real = tflearn.input_data(shape=[None, 400, 400, 1], name='input_disc_real')

# Build Discriminator
disc_fake = discriminator(generator(input_disc_noise))
disc_real = discriminator(input_disc_real, reuse=True)
disc_net = tf.concat([disc_fake, disc_real], axis=0)
# Build Stacked Generator/Discriminator
gen_net = generator(gen_input, reuse=True)
stacked_gan_net = discriminator(gen_net, reuse=True)