search

huawei-noah / Pretrained-IPT

Apache License 2.0
434 stars 63 forks source link

test question #22

Closed Trueman1997 closed 1 year ago

Trueman1997 commented 2 years ago

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

HantingChen commented 2 years ago

You can add "DICM" in https://github.com/huawei-noah/Pretrained-IPT/blob/32ce841c18ca33c31fa15907ac21bbddd1583519/data/__init__.py#L40, and then put the data in /Pretrained-IPT-main/test_data/benchmark/DICM .