search

ttgeng233 / UnAV

Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline (CVPR 2023)
https://unav100.github.io
MIT License
54 stars 4 forks source link

Issue in #9

Closed 1980x closed 8 months ago

1980x commented 8 months ago

Thanks for your work. I am training the model on custom video dataset. While doing evaluation after one epoch, I get error modeling/multimodal_meta_archs.py", line 619, in torch.cat(x) for x in [segs_all, scores_all, cls_idxs_all] RuntimeError: torch.cat(): expected a non-empty list of Tensors terminate called after throwing an instance of 'c10::Error' what(): CUDA error: device-side assert triggered Exception raised from c10_cuda_check_implementation at ../c10/cuda/CUDAException.cpp:31 (most recent call first):

After sometime, figured out that in def inference_single_video() function: topk idxs tensor([94585022332496, 94582502706592, 94585097936080, ..., 94585022005264, 140088139025376, 64], device='cuda:0') pt_idxs tensor([94585098952080, 140088139025376, 64, ..., 94585021827888, 140088139025376, 64], device='cuda:0') are becoming very large.

Can you suggest what could be the issue? Thank you.

1980x commented 8 months ago

There was a small bug in the code. I corrected that.