Open ccapontep opened 1 year ago
Hey, Where did you find the video action recognition model? It isn't in this repo.
Hi, I have been using pytorchvideo that includes the Slowfast model. https://github.com/facebookresearch/pytorchvideo
I have based my training from the example shown there: https://github.com/facebookresearch/pytorchvideo/blob/main/tutorials/video_classification_example/train.py
I found their implementation https://github.com/facebookresearch/pytorchvideo/blob/main/pytorchvideo/models/vision_transformers.py with the weights at https://github.com/facebookresearch/pytorchvideo/blob/main/docs/source/model_zoo.md
Thanks for helping :)
Hey, did you find a solution to this issue?
ref: https://blog.csdn.net/WhiffeYF/article/details/133801160
need add configurations
VIS_MASK:
ENABLE: True
Hello,
I am having problems with the sizes of the videos when training the Slowfast model with kinetics dataset. Here is the error:
The transform of the data is the following:
And PackPathway is as follows:
Returns the following:
The shape of the data after transforming and loading with batch is:
Output is:
The error again being:
But the sizes are matching at dimension 1, in this case the input of data to the model does not have the same size in dimension 3. I have also tried permuting the dimensions to solve this [ C, T, H, W] -> [ T, C, H, W], but it gives a different error. Any idea of how to resolve this please?