Update README.md

This commit is contained in:
ZhongdaoWang 2020-01-29 23:25:09 +08:00 committed by GitHub
parent 66f0225e92
commit 04e7e79818
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23

View file

@ -46,13 +46,13 @@ Please see [DATASET_ZOO.md](https://github.com/Zhongdao/Towards-Realtime-MOT/blo
## Pretrained model and baseline models ## Pretrained model and baseline models
Darknet-53 ImageNet pretrained model: [[DarkNet Official]](https://pjreddie.com/media/files/darknet53.conv.74) Darknet-53 ImageNet pretrained model: [[DarkNet Official]](https://pjreddie.com/media/files/darknet53.conv.74)
Trained models: Trained models with different input resolutions:
|Model| MOTA | IDF1 | IDS | FP | FN | FPS | Link | |Model| MOTA | IDF1 | IDS | FP | FN | FPS | Link |
|-----|------|------|-----|----|----|-----|------| |-----|------|------|-----|----|----|-----|------|
|JDE-1088x608-uncertainty| 74.8| 67.3| 1189| 5558| 21505| 22.2| [[Google Drive]](https://drive.google.com/open?id=1nlnuYfGNuHWZztQHXwVZSL_FvfE551pA) [[Baidu NetDisk]](https://pan.baidu.com/s/1Ifgn0Y_JZE65_qSrQM2l-Q) | |JDE-1088x608| 74.8| 67.3| 1189| 5558| 21505| 22.2| [[Google]](https://drive.google.com/open?id=1nlnuYfGNuHWZztQHXwVZSL_FvfE551pA) [[Baidu]](https://pan.baidu.com/s/1Ifgn0Y_JZE65_qSrQM2l-Q) |
|JDE-864x480-uncertainty| 70.8| 65.8| 1279| 5653| 25806| 20.3| [[Google Drive]]() [[Baidu NetDisk]]() | |JDE-864x480| 70.8| 65.8| 1279| 5653| 25806| 20.3| [[Google]]() [[Baidu]]() |
|JDE-576x320-uncertainty| 63.7| 63.3| 1307| 6657| 32794| 37.9|[[Google Drive]]() [[Baidu NetDisk]]() | |JDE-576x320| 63.7| 63.3| 1307| 6657| 32794| 37.9|[[Google]]() [[Baidu]]() |
The performance is tested on the MOT-16 training set, just for reference. Running speed is tested on an Nvidia Titan Xp GPU. For a more comprehensive comparison with other methods you can test on MOT-16 test set and submit a result to the [MOT-16 benchmark](https://motchallenge.net/results/MOT16/?det=Private). Note that the results should be submitted to the private detector track. The performance is tested on the MOT-16 training set, just for reference. Running speed is tested on an Nvidia Titan Xp GPU. For a more comprehensive comparison with other methods you can test on MOT-16 test set and submit a result to the [MOT-16 benchmark](https://motchallenge.net/results/MOT16/?det=Private). Note that the results should be submitted to the private detector track.