sangyun884 / HR-VITON

Official PyTorch implementation for the paper High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions (ECCV 2022).
831 stars 171 forks source link

IndexError: list index out of range #3

Closed psx2 closed 2 years ago

psx2 commented 2 years ago

Getting the following error when running on Windows.

Traceback (most recent call last):
  File "test_generator.py", line 249, in <module>
    main()
  File "test_generator.py", line 225, in main
    board = SummaryWriter(log_dir=os.path.join(opt.tensorboard_dir, opt.tocg_checkpoint.split('/')[-2], opt.tocg_checkpoint.split('/')[-1], opt.datamode, opt.datasetting))
IndexError: list index out of range

Any idea?

verc3l commented 2 years ago

I am running on a completely clean AWS Linux instance and have run into the same issue.

Upon testing the command python3 test_generator.py, I am greeted with the error:

FileNotFoundError: [Errno 2] No such file or directory: './data/zalando-hd-resize/./data/zalando-hd-resize/test_pairs.txt'

To resolve, I change the parser arguments for 'dataroot' and 'data_list' in test_generator.py to.

parser.add_argument("--dataroot", default="./data/zalando-hd-resized/")
parser.add_argument("--data_list", default="test_pairs.txt")

This seemingly fixed the FileNotFoundError issue, but presented a new error:

Traceback (most recent call last):
  File "test_generator.py", line 249, in <module>
    main()
  File "test_generator.py", line 225, in main
    board = SummaryWriter(log_dir=os.path.join(opt.tensorboard_dir, opt.tocg_checkpoint.split('/')[-2], opt.tocg_checkpoint.split('/')[-1], opt.datamode, opt.datasetting))
IndexError: list index out of range

Please can you ensure the code and instructions have been tested on a clean instance @koo616 @sangyun884.

Arnavgoyal00 commented 2 years ago

@psx2 @verc3l I need help to preprocess the input data, particularly in human segmentation .

sangyun884 commented 2 years ago

@verc3l Did you follow the test command we instructed?

koo616 commented 2 years ago

@verc3l We fixed it. Please check the updated readme and try it again.