irvingzhang0512

I met the same problem because I remove `build` folder........ In folly, `build` folder is not designed for cmake build....

@hukkai You can take a look at [kinetics-dataset](https://github.com/cvdfoundation/kinetics-dataset), maybe CVDF has already provide a link to download ava-kinetics videos and annotations

it will be nice if mmaction2 could support ava dataset and spatio-temporal action detection models.

Very happy to have spatio-temporal action detection model today... Two related features could be very helpful: 1. spatio-temporal action detection online/video demo. 2. train spatio-temporal action detection models with custom...

Maybe MMAction2 could support some of the models and datasets from [PytorchVideo](https://github.com/facebookresearch/pytorchvideo)

摄像头一般提供rtsp推流，会有一个 rtsp 地址。把这个地址直接输入到 `cv2.VideoCapture` 就能读到实时视频流了

I don't think `pytorch2onnx.py` supports spatio-temporal action detection models.

> @irvingzhang0512 thanks for quick response. if pytorch2onnx.py dosn't support then any other alternative to convert it onnx or tensorrt to optimize the model. Since spatio-temporal action detecction models use...

I don't think MMAction2 support exxporting spatio-temporal action detection models for now.

[this paper](https://arxiv.org/abs/2012.06567) shows that random rotation may help