why the network's input shape is 1 24 224 224

mit-han-lab / temporal-shift-module

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

https://arxiv.org/abs/1811.08383

MIT License

2.07k stars 417 forks source link

Closed dengfenglai321 closed 2 years ago

dengfenglai321 commented 2 years ago

why the network's input shape is 1 24 224 224 but bot 1 8 3 224 224? how to understand 24?

tonylins commented 2 years ago

8 frames with 3 channels each frame.