如何针对固定数据大小增加deconv2d过滤器的大小？

Question

我正在尝试调整此DCGAN代码,以便能够使用2x80数据样本.

所有发生器层都不是tf.nn.deconv2dh0,即ReLu.目前每级的生成器过滤器大小:

Generator: h0: s_h16 x s_w16: 1  x  5
Generator: h1: s_h8 x s_w8: 1  x  10
Generator: h2: s_h4 x s_w4: 1  x  20
Generator: h3: s_h2 x s_w2: 1  x  40
Generator: h4: s_h x s_w: 2  x  80

因为我的数据的性质,我想他们是2×...,即用于过滤器是最初产生2 x 5,2 x 10,2 x 20,2 x 40,和2 x 80.但是,当我只是手动输入s_h16 = 2 * s_h16等等时s_h2 = 2 * s_h2,我遇到以下错误:

ValueError: Shapes (64, 1, 40, 64) and (64, 2, 40, 64) are not compatible

所以我知道错误发生在h3级别,但是我无法完全跟踪它(64这里是批量大小).任何想法如何解决这个问题？

---

编辑:编辑后的DCGAN代码在此存储库中,在DCGAN-tensorflow设置完成后,您必须将Data_npy文件夹放入DCGAN-tensorflow/data文件夹中.

然后运行python main.py --dataset Data_npy --input_height=2 --output_height=2 --train将为您提供我得到的错误.

完整错误回溯如下所示:

Traceback (most recent call last):
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 560, in merge_with
    new_dims.append(dim.merge_with(other[i]))
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 135, in merge_with
    self.assert_is_compatible_with(other)
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 108, in assert_is_compatible_with
    % (self, other))
ValueError: Dimensions 1 and 2 are not compatible

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "main.py", line 97, in <module>
    tf.app.run()
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "main.py", line 80, in main
    dcgan.train(FLAGS)
  File "/home/marija/DCGAN-tensorflow/model.py", line 180, in train
    .minimize(self.g_loss, var_list=self.g_vars)
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/training/optimizer.py", line 315, in minimize
    grad_loss=grad_loss)
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/training/optimizer.py", line 386, in compute_gradients
    colocate_gradients_with_ops=colocate_gradients_with_ops)
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 580, in gradients
    in_grad.set_shape(t_in.get_shape())
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 413, in set_shape
    self._shape = self._shape.merge_with(shape)
  File "/home/marija/.local/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 564, in merge_with
    (self, other))
ValueError: Shapes (64, 1, 40, 64) and (64, 2, 40, 64) are not compatible

Answer 1

在你的 ops.py 文件中

您的问题来自反卷积过滤器中的跨步大小，将conv2d和 的标题修改deconv2d为：

def conv2d(input_, output_dim, 
       k_h=5, k_w=5, d_h=1, d_w=2, stddev=0.02,
       name="conv2d"):

def deconv2d(input_, output_shape,
       k_h=5, k_w=5, d_h=1, d_w=2, stddev=0.02,
       name="deconv2d", with_w=False):

就这样它开始为我训练。但我没有检查输出。

问题是考虑输入的形状，高度按 2（d_h 的原始值）进行拉伸将(64, 1, 40, 64)在反向传播期间产生形状。（因为你只有2个值）

另外，您可能会认为，k_h=5当k_h=2您只有 2 个元素时，在高度上采用 5 个元素并没有多大意义。