Jean-Paul Ainam

Hi! I also wish to know how he visualized the attention masks

Hi, did you manage to get the visualization of the learned filters? @liyaguang by the way, what is you advise if we want to visualize the strength of connectivity (i.e....

Hi. I tried to introduce the re-weighting module. But can't figure out the right values. According to the original paper  ``` m = 28 # the number of attributes...

You are right, there is a big gap between the results reported in the paper and the results i get when trained on two partial or occluded persion reid datasets....

@hh23333 The PCB model you shared didn't work. So, i had to train my own PCB but using your code. 1. The result i get with the PCB baseline on...

@chenxiangzZ Thanks. I also changed the issue title to reflect what was discussed here.

```python python scripts/main.py --load-pose --root ../PVPM_experiments/data \ -s market1501\ -t partial_reid occlusion_reid p_duke\ .... ``` In thes training parameters. the source dataset `-s` is set to `market1501` while the target...

@chenxiangzZ pls, can you show me the results of the PCB baseline evaluation alone on market1501 dataset? These are my results ```python ##### Evaluating market1501 (source) ##### Extracting features from...

@chenxiangzZ I mean the author's PCB baseline. Maybe the author's PCB baseline on market1501 dataset is higher than ours. We got the same `mAP: 77.5, rank-1: 92.7` on our PCB...

That's really weird. the authors' PCB baseline has a lower performance than ours. But when using it with PVPM, it increases the final results.