Closed vitacon closed 3 months ago
Hi @vitacon. Thank you so much for the interest in our project and I feel so sorry for the trouble you are facing with. Let me try to explain to you one by one. Hope it will be helpful.
Here is some information might be useful: We are doing some work based on patchfusion and we entirely reconstruct the current code base. We are using torch2.0+ so the env would be more friendly. After rebuilding, the log is also better. The model can also support various number of splitting patches (like using 2x2 patches for 2k image or more user-friendly settings). It would be released soon.
Thanks @zhyever!
Just a few additional notes:
Actually, "Grand Theft Auto" was the only meaning I could think of but (not knowing the dataset) it did not make any sense to me. =} I know that writing documentation is quite annoying but I think the two models should be explained in readme.md
.
By the way, did you perform any numeric comparison of their outputs?
Hm, I suppose I could use Image Magick, merge 4 images together (2x2), feed it to PatchFusion and then split the output back to 4 images. Or learn a bit of Python syntax and do the same thing directly in infer_user.py
. However, if the new version is going to be released soon, I think I will just wait for it. =)
Thanks.
Ideally, the new release would be at the end of March. Thanks for your advices and patience.
Thanks again @zhyever!
"It makes a lot of sense. As for 2k images, you can split them to 2x2 patches covered the whole image, which will save time. However, it would be tough to modify the codes right now, because there are many hacking codes..."
Where would this be done? Is there an argument for this?
@vitacon @noobtoob4lyfe Please check the current version of inference instructions. All of discussed items are supported now
@vitacon I'm not seeing the argument for changing the number of patches to 2x2.
Please check this example usage in the readme
Hello @zhyever, I started experimenting with PathFusion yesterday (Windows 10 + Anaconda) and I still don't understand some things.
It seemed the import of .env passed (the output was so long I could see only the end of it) but the demo still crashed. I had to (re?)install several packges by hand (torchvision, torch and timm), but that's not really a question. =)
infer_user.py throws quite a lot of warnings so the console becomes very messy:
Params passed to Resize transform: width: 512 height: 384 resize_target: True keep_aspect_ratio: False ensure_multiple_of: 32 resize_method: minimal
Current image resolution: (2160, 3840) Current crop size: (540, 960) build pretrained condition model from None img_size [384, 512]