minar09 / ACGPN

"Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content",CVPR 2020. (Modified from original with fixes for inference)
https://github.com/switchablenorms/DeepFashion_Try_On
77 stars 70 forks source link

ValueError: not enough values to unpack (expected 16, got 10) #13

Closed maguro27 closed 3 years ago

maguro27 commented 3 years ago

Thank you for your great job! However, the training script of this repository does not work. I meet the ValueError when run python train.py. In line 161 of the train.py,

ValueError: not enough values to unpack (expected 16, got 10)

I checked the models/pix2pixHD_model.py. Thus, the forward function of pix2pixHD_model.py returns only 10 arguments. Now, I confirm the Unet class of the models/networks.py does not return rx, ry, cx, and cy arguments. After that, I add the rx, ry, cx, and cy arguments to the return function of the forward function of the Unet class.

However, I cannot find refined, rg, and cg arguments of line 161 of the train.py.

Please fix the training scripts so it works. Thanks.

minar09 commented 3 years ago

Hi, @maguro27 , thanks for your comment. However, I am sorry to let you know that I have only tested and modified the testing script. The training scripting was copied as it is from the original repository and I did not run it. For more details, I'd recommend you refer to the repository from the original authors.

arink20 commented 1 year ago

Thank you for your great job! However, the training script of this repository does not work. I meet the ValueError when run python train.py. In line 161 of the train.py,

ValueError: not enough values to unpack (expected 16, got 10)

I checked the models/pix2pixHD_model.py. Thus, the forward function of pix2pixHD_model.py returns only 10 arguments. Now, I confirm the Unet class of the models/networks.py does not return rx, ry, cx, and cy arguments. After that, I add the rx, ry, cx, and cy arguments to the return function of the forward function of the Unet class.

However, I cannot find refined, rg, and cg arguments of line 161 of the train.py.

Please fix the training scripts so it works. Thanks.

@maguro27 can i see your networks.py , train.py and how did u change it to get rx,ry,cx,cy,rg,cg ?