Thank you for providing such detailed code and tutorial !!
And I also successfully trained on my own dataset.
But when I want to see the results on may validation set some errors occur.
Like this:
Traceback (most recent call last):
File "train_net.py", line 243, in
main()
File "train_net.py", line 239, in main
run_test(cfg, model, args.distributed, args.motion_specific)
File "train_net.py", line 137, in run_test
inference(
File "/Jyun_an/DiffusionVID/mega_core/engine/inference.py", line 142, in inference
predictions = compute_on_dataset(model, data_loader, device, bbox_aug, cfg.MODEL.VID.METHOD, inference_timer, cfg.TEST.SEQ_NMS)
File "/Jyun_an/DiffusionVID/mega_core/engine/inference.py", line 49, in compute_on_dataset
output = model(images)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 881, in _call_impl
result = self.forward(*input, *kwargs)
File "/opt/conda/lib/python3.8/site-packages/apex/amp/_initialize.py", line 196, in new_fwd
output = old_fwd(applier(args, input_caster),
File "/Jyun_an/DiffusionVID/mega_core/modeling/detector/diffusion_det.py", line 336, in forward
return self._forward_test(images["cur"], infos, targets)
File "/Jyun_an/DiffusionVID/mega_core/modeling/detector/diffusion_det.py", line 521, in _forward_test
feats_cur.append(torch.cat([self.feats[i][j] for i in range(range_start, range_end)]))
File "/Jyun_an/DiffusionVID/mega_core/modeling/detector/diffusion_det.py", line 521, in
feats_cur.append(torch.cat([self.feats[i][j] for i in range(range_start, range_end)]))
IndexError: deque index out of range
And I have no idea how to deal with this.......
Is it a problem with model setting or data reading?
andy-sasa
commented
7 months ago
Thank you for providing such detailed code and tutorial !! And I also successfully trained on my own dataset. But when I want to see the results on may validation set some errors occur.
Like this:
Traceback (most recent call last): File "train_net.py", line 243, in
main()
File "train_net.py", line 239, in main
run_test(cfg, model, args.distributed, args.motion_specific)
File "train_net.py", line 137, in run_test
inference(
File "/Jyun_an/DiffusionVID/mega_core/engine/inference.py", line 142, in inference
predictions = compute_on_dataset(model, data_loader, device, bbox_aug, cfg.MODEL.VID.METHOD, inference_timer, cfg.TEST.SEQ_NMS)
File "/Jyun_an/DiffusionVID/mega_core/engine/inference.py", line 49, in compute_on_dataset
output = model(images)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 881, in _call_impl
result = self.forward(*input, *kwargs)
File "/opt/conda/lib/python3.8/site-packages/apex/amp/_initialize.py", line 196, in new_fwd
output = old_fwd(applier(args, input_caster),
File "/Jyun_an/DiffusionVID/mega_core/modeling/detector/diffusion_det.py", line 336, in forward
return self._forward_test(images["cur"], infos, targets)
File "/Jyun_an/DiffusionVID/mega_core/modeling/detector/diffusion_det.py", line 521, in _forward_test
feats_cur.append(torch.cat([self.feats[i][j] for i in range(range_start, range_end)]))
File "/Jyun_an/DiffusionVID/mega_core/modeling/detector/diffusion_det.py", line 521, in
feats_cur.append(torch.cat([self.feats[i][j] for i in range(range_start, range_end)]))
IndexError: deque index out of range
And I have no idea how to deal with this.......
Is it a problem with model setting or data reading?