pilhyeon / learning-action-completeness-from-points Goto Github PK

Excuse me, what methuod do you use to extract the feature of thumos14? Is it I3D?

Hello, when using your code to reproduce BEOID and GTEA datasets, the result is very different from the paper. Can you tell me how you do it?

Thanks for your excellent job!
I am confused why express video-level probability by that:
vid_score = (torch.mean(topk_scores, dim=1) * vid_labels) + (torch.mean(cas_sigmoid[:,:,:-1], dim=1) * (1 - vid_labels))
Inconsistent between training and testing.

Hello author, I encountered this error when running your code and cannot solve it. What is the reason? The environment and dependent libraries I configured according to your documentation are the same.

Traceback (most recent call last):
File "./main.py", line 21, in
config = Config(args)
File "/home/mcy/miniconda3/envs/python36/lib/python3.6/site-packages/config/init.py", line 709, in init
self.load(stream_or_path)
File "/home/mcy/miniconda3/envs/python36/lib/python3.6/site-packages/config/init.py", line 803, in load
items = p.container()
File "/home/mcy/miniconda3/envs/python36/lib/python3.6/site-packages/config/parser.py", line 285, in container
self.advance()
File "/home/mcy/miniconda3/envs/python36/lib/python3.6/site-packages/config/parser.py", line 130, in advance
self.token = self.tokenizer.get_token()
File "/home/mcy/miniconda3/envs/python36/lib/python3.6/site-packages/config/tokens.py", line 997, in get_token
c = get_char()
File "/home/mcy/miniconda3/envs/python36/lib/python3.6/site-packages/config/tokens.py", line 802, in get_char
c = self.stream.read(1)
AttributeError: 'Namespace' object has no attribute 'read'

Hi, thanks for your excellent job!
May I ask if the source code and extracted feature on ActivityNet will be released？

Hello, thanks for your excellent job. I am interested in your work so much!
May I ask if the extracted features on ActivityNet, GTEA and BEOID will be released？

Hello, thanks for your excellent job. But I have some questions about the code. What does stored_info['new_dense_anno'] correspond to in the paper?

Thanks for making this awesome work publicly available !

I wanted to know what is the meaning if the term "transcript" in "search.py" ? I cannot understand the pattern why sometimes [0,1] is given and [1] is used sometimes. Can you kndly elaborate ?

Hello, in thumbos14, CliffDiving is a subclass of Diving, and the action instances of CliffDiving in the annotation file also belong to Diving. Why don't you use this prior knowledge to remove the action instance of CliffDiving class in the Diving class during training and add a Diving class for each predicted CliffDiving action instance during post-processing?
I think an action instance belonging to two categories may make the training difficult to converge.

Is there any trick to reproduce the result of GTEA , could you please giving config.txt for this dataset and it will be convenient for reproducing. Thank you.@Pilhyeon

Thanks for your job, Is there a link of Baidu cloud ？

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?

Hello, thank you very much for bringing inspiring work. I am a beginner and would like to ask you why some fully supervised methods, such as actionformer, use feature lengths that are inconsistent with the feature lengths you provide. Is it because i3d uses different sampling rates when extracting features?