neuralchen / asmagan Goto Github PK

Hi! Could you please check your pre-trained model. The follow links is no found. Thank you
https://github.com/neuralchen/ASMAGAN/releases/download/v.1.0/ASMAfinal.zip

Hi

the link to the pretrained weights is broken. Could you please provide an alternative link

Hi can you please add a license file

test code change aspect ratio of input images
so output images are deformed
to fix this i make some correction at "test_data_loader_resize.py"

using the official command: python main.py --mode test --cuda 0 --version ASMAfinal --dataloader_workers 8 --testImgRoot ./bench/ --nodeName localhost --checkpoint 350000 --testScriptsName common_useage --specify_sytle 8

then error happened
Generator Script Name: Conditional_Generator_asm
11 classes
Finished preprocessing the test dataset, total image number: 25...
/home/ama/anaconda3/envs/ASMA/lib/python3.9/site-packages/torchvision/transforms/transforms.py:332: UserWarning: Argument interpolation should be of type InterpolationMode instead of int. Please, use InterpolationMode enum.
warnings.warn(
Traceback (most recent call last):
File "/home/ama/ASMAGAN/main.py", line 266, in
tester.test()
File "/home/ama/ASMAGAN/test_scripts/tester_common_useage.py", line 50, in test
test_data = TestDataset(test_img,batch_size)
File "/home/ama/ASMAGAN/data_tools/test_data_loader_resize.py", line 36, in init
transform.append(T.Resize(1088,1920))
File "/home/ama/anaconda3/envs/ASMA/lib/python3.9/site-packages/torchvision/transforms/transforms.py", line 336, in init
interpolation = _interpolation_modes_from_int(interpolation)
File "/home/ama/anaconda3/envs/ASMA/lib/python3.9/site-packages/torchvision/transforms/functional.py", line 47, in _interpolation_modes_from_int
return inverse_modes_mapping[i]
KeyError: 1920

Hi I get the following error when running the code:

I would appreciate your help on how to resolve this.

Thank you

Hi I get the following error when running the code:

RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED when calling backward()

I would appreciate your help on how to resolve this.

Thank you!

Gero

Hello team, I would like to finetune your pretrained model for just five new class (total output will be five), how should I use the finetune?
Thank you!

Thank you for your great project.

1. When will the training code be released.
2. I want to get more painters how do I do that, how do I make the training datasets, how much data do I need
3. Looking forward to your reply