Du Ang

I didn't meet this problem when training on multi-GPUs so far. The code has been tested on PyTorch 1.0.1 and PyTorch 1.2. You'd better post more information about the error...

@Adhiyaman-Manickam Just as the above words, you'd better debug by yourself and find the exact line of code caused the error. Without debugging or any information with the lines of...

Thanks for asking! 1. For the 'mm' in 'contextual_attention', I followed the same naming [here](https://github.com/JiahuiYu/generative_inpainting/blob/v1.0.0/inpaint_ops.py#L271). From [this issue](https://github.com/JiahuiYu/generative_inpainting/issues/158), 'mm' indicates the background region after softmax. 2. Sorry, I am not...

It seems that there is a bug in your data or your custom dataset. You may try to assert there is no NaN or Inf in your data. I don't...

@ncherel Thansk for your attention! I just confirmed that there is a mislalignment for the output. Thanks for pointing out it happens in the refined stage. The resullt of `examples/imagenet/imagenet_patches_ILSVRC2012_val_00025892_input.png`...

Awesome! Could you please share your code in a branch/pull request so that other people may learn from it? Thanks for your excellent work!

你用的什么显卡呀？看上去就是显存不够了

看上去总显存是4G，可以试试 batch_size 1 能不能跑起来。如果能跑起来，就可以用小 batch size 跑。

You may try this solution: https://github.com/daa233/generative-inpainting-pytorch/issues/38#issuecomment-717905821

Sorry, I didn't test it with the above examples, and not sure about the details here.