You've mentioned that your work's feature extractions' part was followed https://github.com/piergiaj/pytorch-i3d, but when I tried to apply it to my own datasets, I found that the dimention of layer 'logits.conv3d' is mismatch.
Traceback (most recent call last):
File "extract_features.py", line 88, in
run(mode=args.mode, load_model=args.load_model)
File "extract_features.py", line 51, in run
i3d.load_state_dict(torch.load(load_model))
File "/home/pengfang/.conda/envs/mvit/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1604, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for InceptionI3d:
size mismatch for logits.conv3d.weight: copying a param with shape torch.Size([400, 1024, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([54, 1024, 1, 1, 1]).
size mismatch for logits.conv3d.bias: copying a param with shape torch.Size([400]) from checkpoint, the shape in current model is torch.Size([54]).
Do I need to finetune the I3D on my datasets? Could you tell me how you apply this code to Thumos14?