huawei-noah/Pretrained-IPT

test question

Trueman1997 opened this issue · 1 comments

I put my own test data into /Pretrained-IPT-main/test_data/ in order to check the denoising,then run the following command,but it did not work?can you help me .

python main.py --dir_data /Pretrained-IPT-main/test_data/ --pretrain /Pretrained-IPT-main/pretrained_model/ --data_test DICM --scale 1 --denoise --sigma 30

Traceback (most recent call last):
File "main.py", line 37, in
main()
File "main.py", line 22, in main
loader = data.Data(args)
File "/gaoren/Pretrained-IPT-main/data/init.py", line 35, in init
num_workers=args.n_threads,
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 213, in init
sampler = RandomSampler(dataset)
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/sampler.py", line 94, in init
"value, but got num_samples={}".format(self.num_samples))
ValueError: num_samples should be a positive integer value, but got num_samples=0

You can add "DICM" in

if d in ['Set5', 'Set14', 'B100', 'Urban100', 'Manga109','CBSD68','Rain100L','GOPRO_Large']:
, and then put the data in /Pretrained-IPT-main/test_data/benchmark/DICM .