search

jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.16k stars 250 forks source link

how to prepare pre-trained model for custom dataset #70

Open Chuttyboy opened 1 year ago

Chuttyboy commented 1 year ago

Hai @jfzhang95 @sdxass

I have tried the UCF dataset with X labels and its results are too good. Now how to detect an action for a custom dataset (own dataset)?

If I go with my own dataset how to prepare a pre-trained model?

For example, I want to detect shoplifting detection how to prepare a pre-trained model for this class

Thanks