search

CV-ZMH / human-action-recognition

Multi Person Skeleton Based Action Recognition and Tracking
MIT License
125 stars 26 forks source link

demo.py error #3

Closed MaarufB closed 3 years ago

MaarufB commented 3 years ago

I try to run demo.py script and i've got this error message

Traceback (most recent call last): File "demo.py", line 171, in main() File "demo.py", line 65, in main tracker = get_tracker(tracker_kwargs) File "D:\AI_POSE\human-action-recognition\src\lib\tracker__init__.py", line 11, in get_tracker return trackers[name](kwargs) File "D:\AI_POSE\human-action-recognition\src\lib\tracker\deepsort\deepsort.py", line 15, in init self.extractor = FeatureExtractor(kwargs) File "D:\AI_POSE\human-action-recognition\src\lib\tracker\deepsort\reid_feature_extractor.py", line 43, in init self.extractor = self._load_torch_model(model_path) File "D:\AI_POSE\human-action-recognition\src\lib\tracker\deepsort\reid_feature_extractor.py", line 63, in _load_torch_model state_dict = torch.load(model_path, map_location='cpu')['net_dict'] File "C:\Users\Admin\anaconda3\envs\action-recognition\lib\site-packages\torch\serialization.py", line 386, in load return _load(f, map_location, pickle_module, pickle_load_args) File "C:\Users\Admin\anaconda3\envs\action-recognition\lib\site-packages\torch\serialization.py", line 559, in _load raise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)".format(f.name)) RuntimeError: D:/AI_POSE/human-action-recognition/weights\tracker\deepsort\siamese_mars.pth is a zip archive (did you mean to use torch.jit.load()?)

I am using window 10

CV-ZMH commented 3 years ago

Hi @MaarufB, Thank you for your interest in this project. Can you check your pytorch version? In my case, pytorch==1.7.1. It's just version problem I think. You can check the dependencies in here

MaarufB commented 3 years ago

Thanks for your reply. It's okay now. We're able to run it without installing the tensorrt and we upgrade the version of pytorch.

MaarufB commented 3 years ago

By the way sir, does this project implement RNN or LSTM?

CV-ZMH commented 3 years ago

No, it doesn't yet. Whereas, It's just implemented with MLP layers for the input of a sequence of tracked person's keypoints as window shifting manner. But I am planning to implement action prediction with LSTM or Gated Network in near future.

MaarufB commented 3 years ago

No, it doesn't yet. Whereas, It's just implemented with MLP layers for the input of a sequence of tracked person's keypoints. But I am planning to implement action prediction with LSTM or Gated Network in near future.

Okay sir thank you so much.