p1x31

I've encountered the same problem with converting [GridNet](https://arxiv.org/pdf/1707.07958.pdf) model

How did you install Pytorch? This is probably the solution to your problem: [link](https://discuss.pytorch.org/t/importerror-key-already-registered-with-the-same-priority/86271) Try something like this: pip3 install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio==0.8.1 -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html

Hey! It would be useful to upload some examples to provide the gist of a kind of soapiness you're experiencing Input input with `--HR` flag:  RTX 2080ti output ...

I can reproduce this when running sequentially one after another, but I can not reproduce this with Full Pipeline. Could be related to `h = int(round(oh / 4) * 4)`...

`detection.py` produces two folders input and mask, input containing your original image with the right rescale. After running `detection.py` your command should be `python test.py --Scratch_and_Quality_restore --test_input output/input --test_mask output/mask...

@dotnet-policy-service agree

if anyone will meet the same problem again here is a [solution](https://github.com/dotnet/runtime/issues/102452#issuecomment-2126770795)

Try this ``` # Any image is allowed, but this paticular will build significantly faster # It is a complete copy of #ARG FROM_IMAGE_NAME=nvidia/cuda:12.8.0-devel-ubuntu22.04 ARG FROM_IMAGE_NAME=pytorch/pytorch:2.8.0-cuda12.6-cudnn9-runtime FROM ${FROM_IMAGE_NAME} # Install...