# test, the output_path should be same with that in training process
python main.py --market_path market_path --duke_path duke_path --output_path output_path/ --mode test --resume_test_epoch resume_test_epoch
# visualize the ranked images, the output_path should be same with that in training process
python main.py --market_path market_path --duke_path duke_path --output_path output_path/ --mode visualize --resume_visualize_epoch resume_visualize_epoch
Experiments
1. Tricks we used
Warm up learning rate
Random erasing augmentation (REA)
Label smoothing
Last stride
BNNeck
Note that our implementation uses no the center loss and re-ranking.
2. Settings
We conduct our experiments on 1 GTX1080ti GPU
3. Results (with REA)
Repeat
market2market
market2duke
duke2duke
duke2market
1
0.939 (0.858)
0.290 (0.159)
0.874 (0.767)
0.486 (0.210)
2
0.944 (0.858)
0.295 (0.156)
0.868 (0.765)
0.492 (0.223)
3
0.942 (0.859)
0.281 (0.152)
0.863 (0.765)
0.485 (0.221)
Average
0.942 (0.858)
0.289 (0.156)
0.868 (0.766)
0.488 (0.218)
Paper
0.941 (0.857)
-
0.864 (0.764)
4. Results (without REA)
Repeat
market2market
market2duke
duke2duke
duke2market
1
0.936 (0.824)
0.427 (0.264)
0.849 (0.714)
0.556 (0.269)
Paper
-
0.414(0.257)
-
0.543 (0.255)
5. Visualization of Ranked Images on Market-1501 Dataset (with REA)
Query
Top1
Top2
Top3
Top4
Top5
Top6
Top7
Top8
Top9
Top10
More results can be seen in folder ranked_images/market
Contacts
If you have any question about the project, please feel free to contact with me.