python - 如何为固定数据大小增加 deconv2d 过滤器的大小？

Question

我正在尝试调整这个 DCGAN code能够处理 2x80 数据样本。

全部generator层是 tf.nn.deconv2d 而不是 h0，它是 ReLu。目前每个级别的生成器过滤器大小为:

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

由于我的数据的性质，我希望它们最初生成为 2 x ...，即过滤器为 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 等直到 s_h2 = 2 * s_h2 时，我遇到了以下错误:

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，但我无法完全追踪到它(这里的 64 是批量大小)。任何想法如何解决这个问题？

---

编辑:编辑后的DCGANs代码为in this repository ，在设置 DCGAN-tensorflow 之后 as in the instructions你必须将 Data_npy 文件夹放入 DCGAN-tensorflow/data 文件夹。

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。

完整的错误回溯如下:

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 deconv 过滤器中的跨步大小，将 conv2d 和 deconv2d 的 header 修改为:

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。不过我没有检查输出。

问题在于考虑输入的形状，在反向传播过程中将高度调整 2(d_h 的原始值)将导致 (64, 1, 40, 64) 形状。 (因为你只有2个值)

您可能还想将 k_h=5 更改为 k_h=2，因为当您只有 2 个元素时，在高度上取 5 个元素没有多大意义。