Testing the models

[gitman88]

What would the terminal command be to evaluate the WDSR models with EDSR as backbone?

I added the following to the option.py

parser.add_argument('--r_mean', type=float, default=0.4488, help='Mean of R Channel') parser.add_argument('--g_mean', type=float, default=0.4371, help='Mean of G channel') parser.add_argument('--b_mean', type=float, default=0.4040, help='Mean of B channel') parser.add_argument('--block_feats', type=int, default=128, help='Block feats')

And added the wdsr_a and wdsr_b models to src/model/.

What would the corresponding command for the WDSR be something like this:

python main.py --data_test Set5 --data_range 801-900 --scale 4 --n_resblocks 32 --n_feats 256 --res_scale 0.1 --pre_train download --test_only --self_ensemble

Any help appreciated!

[JiahuiYu]

It should be similar to EDSR testing command. What the error you get for this command?

[gitman88]

Well, it evaluates the data by reporting a nan as PSNR. The data is located at src/data/benchmark and the path in option.py looks like this:

parser.add_argument('--dir_data', type=str, default='/Users/Dev/EDSR-PyTorch/src/data/benchmark', help='dataset directory') parser.add_argument('--dir_demo', type=str, default='../test', help='demo image directory') parser.add_argument('--data_train', type=str, default='B100', help='train dataset name') parser.add_argument('--data_test', type=str, default='B100', help='test dataset name')

When running the output is this:

`Evaluation: 0it [00:00, ?it/s] [Set5 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [Set14 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [B100 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [Urban100 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [DIV2K x4] PSNR: nan (Best: nan @epoch 1) Forward: 0.50s

Saving... Total: 0.50s`

Any ideas what could cause this?

[JiahuiYu]

I have no related experiences on this issue. I would suggest to print out predicted images (and maybe feature map) to debug.

[Ccbov]

Well, it evaluates the data by reporting a nan as PSNR. The data is located at src/data/benchmark and the path in option.py looks like this:

parser.add_argument('--dir_data', type=str, default='/Users/Dev/EDSR-PyTorch/src/data/benchmark', help='dataset directory') parser.add_argument('--dir_demo', type=str, default='../test', help='demo image directory') parser.add_argument('--data_train', type=str, default='B100', help='train dataset name') parser.add_argument('--data_test', type=str, default='B100', help='test dataset name')

When running the output is this:

`Evaluation: 0it [00:00, ?it/s] [Set5 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [Set14 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [B100 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [Urban100 x4] PSNR: nan (Best: nan @epoch 1) 0it [00:00, ?it/s] [DIV2K x4] PSNR: nan (Best: nan @epoch 1) Forward: 0.50s

Saving... Total: 0.50s`

Any ideas what could cause this?

hello, I meet the same problem, could you please give me some advise?