无聊时的自娱自乐

icon indicating an email [email protected]

icon company Tsinghua University icon location Shenzhen icon location PhD candidate from Tsinghua Shenzhen International Graduate School, Tsinghua University.

Results 4 comments of 无聊时的自娱自乐

How to speed up mesh decimation

Did you figure out how to solve it?

Only part of the fake image is clear in AAE tutorial.

When I change the `nn.Conv2d(channels, channels * 2, 5, 4, 2)` to `nn.Conv2d(channels, channels * 2, 5, 2, 2)` (as long as the tranposed convolution layer), the results become corrrect....

There are not many bugs in your code.

Shit code. I have to re-write many parts by myself. I don't understand that why there are so many stars. The code doesn't have a clear readme file.

Entropy loss

Agreed, the entropy loss doesn't make any sense to me.