Question

我正在尝试使用以下this将script pix2pix GAN代码翻译为Tensorflow 1.0.0，如Tensorflow文档中所述，但我不断收到以下错误：

ValueError：变量d_h0_conv / w / Adam /不存在，或者不存在使用tf.get_variable（）创建。你的意思是设置reuse = None in VarScope？

这是Adam优化器部分：

 d_optim = tf.train.AdamOptimizer(args.lr, beta1=args.beta1) \
.minimize(self.d_loss, var_list=self.d_vars)

d_vars是：

t_vars = tf.trainable_variables()

self.d_vars = [var for var in t_vars if 'd_' in var.name]

鉴别码：

    def discriminator(self, image, y=None, reuse=False):
        # image is 256 x 256 x (input_c_dim + output_c_dim)
        if reuse:
            tf.get_variable_scope().reuse_variables()
        else:
            assert tf.get_variable_scope().reuse == False

        h0 = lrelu(conv2d(image, self.df_dim, name='d_h0_conv'))
        # h0 is (128 x 128 x self.df_dim)
        h1 = lrelu(self.d_bn1(conv2d(h0, self.df_dim*2, name='d_h1_conv')))
        # h1 is (64 x 64 x self.df_dim*2)
        h2 = lrelu(self.d_bn2(conv2d(h1, self.df_dim*4, name='d_h2_conv')))
        # h2 is (32x 32 x self.df_dim*4)
        h3 = lrelu(self.d_bn3(conv2d(h2, self.df_dim*8, d_h=1, d_w=1, name='d_h3_conv')))
        # h3 is (16 x 16 x self.df_dim*8)
        h4 = linear(tf.reshape(h3, [self.batch_size, -1]), 1, 'd_h3_lin')
  return tf.nn.sigmoid(h4), h4

过渡到Tensorflow 1.0.0

0 个答案: