Fatemeh Behrad

Hi ,yes it can by model = delete_channels(model, layer_2, [0,4,67])

Yes it supports 3D convnet.

You are right. By default, the UpSampling2D layer in tensorflow will use a nearest neighbor algorithm to fill in the new rows and columns. This has the effect of simply...

I have the same problem

> I've tested the code on windows. It works perfectly.

I faced a similar problem. The problem was due to ratio_gout in './configs/training/generator/ffc_resnet_075'. I set it to zero by mistake while it must equal 0.75. Changing its value solved my...

> Check this issue： [DQiaole/ZITS_inpainting#7](https://github.com/DQiaole/ZITS_inpainting/issues/7) Thank you so much for your quick response.

> Could you install `xformers` and accelerate`and see if that resolves the issue? Running the efficient attention requires you to have`xformers` installed. Yes, during the inference, xformers accelerate the process...

> So in case you have not noticed: Paella is available on huggingface, meanwhile, [just follow this link](https://huggingface.co/spaces/pcuenq/paella). Can you please provide its inpainting version too?

> hello，I have commented this line of code, but I still encounter the following problem. How can I solve this problem?   I have the same problem. :(