search

Dawn-LX / VidVRD-tracklets

Video Visual Relation Detection (VidVRD) tracklets generation. also for ACM MM Visual Relation Understanding Grand Challenge
39 stars 9 forks source link

Error while detecting frame-level object proposals #3

Open yogesh-iitj opened 2 years ago

yogesh-iitj commented 2 years ago

I followed the steps of MEGA installations and everything went well, but during the detection of frame-level object proposals, I am getting this error:

"raise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)".format(f.name)) RuntimeError: MEGA/training_dir/COCO34ORfreq32_4gpu/model_0180000.pth is a zip archive (did you mean to use torch.jit.load()?)"

Any solution? PS: command used: CUDA_VISIBLE_DEVICES=0 python MEGA/tools/test_net.py --config-file MEGA/configs/MEGA/inference/VidORval_freq1_0024.yaml MODEL.WEIGHT MEGA/training_dir/COCO34ORfreq32_4gpu/model_0180000.pth OUTPUT_DIR MEGA/training_dir/COCO34ORfreq32_4gpu/inference

Dawn-LX commented 2 years ago

aise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)".format(f.name))

this seems a pytorch-version issue, refer https://github.com/pytorch/pytorch/issues/43766