mirror of https://github.com/JDAI-CV/fast-reid.git
4629172a90
|
||
|---|---|---|
| .. | ||
| configs | ||
| kdreid | ||
| README.md | ||
| train_net.py | ||
README.md
Model Distillation in FastReID
This project provides a training script of small model for both fast inference and high accuracy.
Datasets Prepration
- Market1501
- DukeMTMC-reID
- MSMT17
Train and Evaluation
# a demo on DukeMTMC-reID dataset
# please see more in ./configs
# train BagTricksIBN50 as teacher model
python3 projects/DistillReID/train_net.py --config-file projects/DistillReID/configs/DukeMTMC/bot50ibn.yml
# train BagTricksIBN18 as student model
python3 projects/DistillReID/train_net.py --config-file projects/DistillReID/configs/DukeMTMC/KD-bot50ibn-bot18ibn.yml --kd
Experimental Results and Trained Models
Settings
All the experiments are conducted with a P40 GPU and
- CPU: Intel(R) Xeon(R) CPU E5-2683 v4 @ 2.10GHz
- GPU：Tesla P40 (Memory 22919MB)
DukeMTMC-reID
| Rank-1 (mAP) / Q.Time/batch(128) | Student (BagTricks) | ||||
|---|---|---|---|---|---|
| IBN-101 | IBN-50 | IBN-34 | IBN-18 | ||
| Teacher (BagTricks) | IBN-101 | 90.8(80.8)/0.3395s | 90.8(81.1)/0.1984s | 89.63(78.9)/0.1760s | 86.96(75.75)/0.0854s |
| IBN-50 | - | 89.8(79.8)/0.2264s | 88.82(78.9)/0.1761s | 87.75(76.18)/0.0838s | |
| IBN-34 | - | - | 88.64(76.4)/0.1766s | 87.43(75.66)/0.0845s | |
| IBN-18 | - | - | - | 85.50(71.60)/0.9178s | |
Market-1501
| Rank-1 (mAP) / Q.Time/batch(128) | Student (BagTricks) | ||||
|---|---|---|---|---|---|
| IBN-101 | IBN-50 | IBN-34 | IBN-18 | ||
| Teacher (BagTricks) | IBN-101 | 95.43(88.95)/0.2698s | 95.19(89.52)/0.1791s | 94.51(87.82)/0.0869s | 93.85(85.77)/0.0612s |
| IBN-50 | - | 95.25(88.16)/0.1823s | 95.13(87.28)/0.0863s | 94.18(85.81)/0.0614s | |
| IBN-34 | - | 94.63(84.91)/0.0860s | 93.71(85.20)/0.0620s | ||
| IBN-18 | - | - | - | 92.87(81.22)/0.0615s | |
| Average Q.Time | 0.2698s | 0.1807s | 0.0864s | 0.0616s | |
MSMT17
| Rank-1 (mAP) / Q.Time/batch(128) | Student (BagTricks) | ||||
|---|---|---|---|---|---|
| IBN-101 | IBN-50 | IBN-34 | IBN-18 | ||
| Teacher (BagTricks) | IBN-101 | 81.95(60.51)/0.2693s | 82.37(62.08)/0.1792s | 81.07(58.56)/0.0872s | 77.77(52.77)/0.0610s |
| IBN-50 | - | 80.18(57.80)/0.1789s | 81.28(58.27)/0.0863s | 78.11(53.10)/0.0623s | |
| IBN-34 | - | 78.27(53.41)/0.0873s | 77.65(52.82)/0.0615s | ||
| IBN-18 | - | - | - | 74.11(47.26)/0.0621s | |
| Average Q.Time | 0.2693s | 0.1801s | 0.0868s | 0.0617s | |
Contact
This project is conducted by Guan'an Wang (guan.wang0706@gmail) and Xingyu Liao.