[ALGORITHM]
@inproceedings{zhu2017deep,
title={Deep feature flow for video recognition},
author={Zhu, Xizhou and Xiong, Yuwen and Dai, Jifeng and Yuan, Lu and Wei, Yichen},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={2349--2358},
year={2017}
}We observe around 1 mAP fluctuations in performance, and provide the best model.
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP@50 | Config | Download |
|---|---|---|---|---|---|---|---|
| R-50-DC5 | pytorch | 7e | 2.50 | 44.0 | 70.3 | config | model | log |
| R-101-DC5 | pytorch | 7e | 3.25 | 39.8 | 73.5 | config | model | log |