mon*_*art 5 python tensorflow pytorch
我想用tensorflow重写pytorch的torch.nn.functional.unfold
函数:
#input x:[16, 1, 50, 36]
x = torch.nn.functional.unfold(x, kernel_size=(5, 36), stride=3)
#output x:[16, 180, 16]
Run Code Online (Sandbox Code Playgroud)
我尝试使用该功能tf.extract_image_patches()
:
x = tf.extract_image_patches(x,ksizes=[1, 1,5, 98],strides=[1, 1, 3, 1], rates=[1, 1, 1, 1],padding='VALID')
输入x.shape
:[16,1,64,98]
我得到输出x.shape
:[16,1,20,490]
然后我将 重塑X
为[16,490,20]
,这正是我所期望的。
但是当我输入数据时出现错误:
UnimplementedError (see above for traceback): Only support ksizes across space.
[[Node:hcn/ExtractImagePatches = ExtractImagePatches[T=DT_FLOAT, ksizes=[1, 1, 5, 98], padding="VALID", rates=[1, 1, 1, 1], strides=[1, 1, 3, 1], _device="/job:localhost/replica:0/task:0/device:GPU:0"](hcn/Reshape)]]
Run Code Online (Sandbox Code Playgroud)
我如何使用tensorflow重写pytorchtorch.nn.functional.unfold
函数来更改X
?
x = tf.reshape(x, [16, 50, 36, 1])
x = tf.extract_image_patches(x, ksizes=[1, 4, 98, 1], strides=[1, 4, 1, 1], rates=[1, 1, 1, 1], padding='VALID')
Run Code Online (Sandbox Code Playgroud)
归档时间: |
|
查看次数: |
1170 次 |
最近记录: |