tsn-pytorch icon indicating copy to clipboard operation
tsn-pytorch copied to clipboard

Temporal Segment Networks (TSN) in PyTorch

Results 44 tsn-pytorch issues
Sort by recently updated
recently updated
newest added

I downloaded the bn_inception pth file, and train, but error occurs that : Runtime error size mismatch for conv1_7x7_s2_bn.weight copying a param with shape for torch.Size([1, 64]) from checkpoint, the...

I have pre-download `bn_inception.pth`,and part of error info as follow: > File "D:\hiicy\documents\files\tsn-pytorch\tf_model_zoo\bninception\pytorch_load.py", line 35, in __init__ self.load_state_dict(model_zoo.load_url(weight_url)) File "D:\hiicy\Anaconda\envs\red\lib\site-packages\torch\nn\modules\module.py", line 845, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading...

Would you share the trained models in pytorch?

Hello everyone, Has anyone successfully converted ActivityNet pre-trained weights into Pytorch TSN?

Hi. Why do you subtract 'new_length' from 'num_frames' and then divide by 'num_segments' to calculate 'average_duration' ? Can we not directly divide 'num_frames' by 'num_segments' to get the 'average_duration' ?...

当我用pytorch1.7版本的gpu来跑这个程序的时候,老报下面的错误,请问怎么解决? File "/data/miniconda3/lib/python3.7/site-packages/torch/autograd/function.py", line 160, in __call__ -- 45 |   | "Legacy autograd function with non-static forward method is deprecated. " 46 |   | RuntimeError: Legacy autograd function with non-static...

I am trying to train action detection model using TSN network for a different custom dataset. In the original TSN paper it is mentioned that along with rgb data, rgb...

Hello Many thanks for sharing your code, which looks fantastic. Is it possible for you to explain that the procedure of live video test such as webcam camera? Thank you

Hi,i run this project in google colab and install mmaction2 to run build_file_list.py, but i encounter the error `No module named 'mmaction.datasets.utils'`. I know is the mmaction problem. I wonder...