Hello, I'm really happy that I can use several action recognition models from you guys.
I was using slowfast model from gluoncv and just realized the affect classification task that I'm doing might get big improvement if I can also provide audio modality.
Regarding this, I wondered if you guys can provide the AVSlowFast model that we can use in model_zoo.
I've tried using AVSlowFast model implemented by PyTorch but they didn't provide the inference code and the criticial thing is that they also require GPU when training/testing and inferencing.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Hello, I'm really happy that I can use several action recognition models from you guys.
I was using slowfast model from gluoncv and just realized the affect classification task that I'm doing might get big improvement if I can also provide audio modality.
Regarding this, I wondered if you guys can provide the AVSlowFast model that we can use in model_zoo.
I've tried using AVSlowFast model implemented by PyTorch but they didn't provide the inference code and the criticial thing is that they also require GPU when training/testing and inferencing.
Could you help me on this?