search

2y7c3 / Super-Resolution-Neural-Operator

Super-Resolution Neural Operator, in CVPR 2023
MIT License
137 stars 12 forks source link

Potential Bug in demo.py #1

Closed Mingyuan1997 closed 1 year ago

Mingyuan1997 commented 1 year ago

Thanks for your contribution! There might be a small dimension bug in the demo.py. Could you help me out?

python demo.py --input input.jpg --model save/rdn_epoch-1000.pth --scale 2 --output output.png torch.Size([3, 135, 240]) Traceback (most recent call last): File "/superresolution/Super-Resolution-Neural-Operator/demo.py", line 42, in pred = model(((img - 0.5) / 0.5).cuda().unsqueeze(0),coord.unsqueeze(0), cell_factorcell.unsqueeze(0)) File "/anaconda3/envs/sr5/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(input, *kwargs) File "/superresolution/Super-Resolution-Neural-Operator/models/sronet.py", line 103, in forward return self.query_rgb(coord, cell) File "/superresolution/Super-Resolution-Neural-Operator/models/sronet.py", line 77, in query_rgb rel_cell[:,1] = feat.shape[-1] IndexError: index 1 is out of bounds for dimension 1 with size 1

2y7c3 commented 1 year ago

The bug has been fixed, thank you for your attention.