Transpose convolution parameters

[mrgloom]

In downsampling part nn.ConvTranspose2d with kernel_size=3, stride=2 is used but seems with these parameters at some parts 3x3 kernel will cover only one input pixel, seems this will lead to checkerboard artifacts. Is it true? or maybe it 'was fixed' somewhere in other place of network for example conv with large kernel size at output?
https://github.com/NVIDIA/pix2pixHD/blob/master/models/networks.py#L203

https://github.com/vdumoulin/conv_arithmetic/blob/master/gif/padding_strides_odd_transposed.gif

[vatsalag99]

Hi, I am following up on this. Currently, my images have few gridding effects, however, would this be fixed when training with the local enhancer or would I need to restart training on the global generator?

[liujiaoshou17]

Hi, I am following up on this. Currently, my images have few gridding effects, however, would this be fixed when training with the local enhancer or would I need to restart training on the global generator?

I also had the same problem，did you solve it