pytorch / vision

Datasets, Transforms and Models specific to Computer Vision
https://pytorch.org/vision
BSD 3-Clause "New" or "Revised" License
16.29k stars 6.96k forks source link

[Newbie Question About fasterrcnn_resnet50_fpn]There are no outputs when evaluating on validation set #2155

Closed weirdseed closed 4 years ago

weirdseed commented 4 years ago

I trained my dataset for several times on training set using pretrained weights, but there are no values in validation outputs. [{'boxes': tensor([], device='cuda:0', size=(0, 4), grad_fn=<StackBackward>), 'labels': tensor([], device='cuda:0', dtype=torch.int64), 'scores': tensor([], device='cuda:0', grad_fn=<IndexBackward>)}, {'boxes': tensor([], device='cuda:0', size=(0, 4), grad_fn=<StackBackward>), 'labels': tensor([], device='cuda:0', dtype=torch.int64), 'scores': tensor([], device='cuda:0', grad_fn=<IndexBackward>)}]

mthrok commented 4 years ago

Hi

Could you provide a minimal complete code example so that we can reproduce this?

weirdseed commented 4 years ago

Hi

Could you provide a minimal complete code example so that we can reproduce this?

Thanks. I think I found the problem, and it's solved!