Self-Similarity-Grouping

Self-Similarity-Grouping copied to clipboard

How to do PK sampler to ensure the calculating of three triplet losses when the labels pf one image are different?

4

你好，有两个问题想要请教一下 1. 由于每张图片根据三个聚类结果有三个标签，代码里是根据第一个标签进行PK采样得到一个batch的图片数据，来进行triplet loss的计算。 但是，如何保证这个batch里的每一张图片在根据后两个聚类结果打上伪标签时，在这个batch中能找到正样本来保证triplet loss的正确计算呢？ 2. 在selftraining.py文件中的compute_dist(）函数中采用了源域数据特征来计算距离，怎么解释呢？我看论文里并没有提到

wangyujie413

Cannot obtain the reported performance by directly running the run.sh

4

Hi, I would like to thank you for releasing the codes in the first place. Following the readme.md, we directly run the run.sh without any modification, but fail to obtain...

Reply1999

dataset写的比较难懂

1

写的冗长又完全没有必要，谁会去从解压文件开始

guanyonglai

Hi, Thank you for the interesting paper and sharing the code. I am currently working on a project based on your implementation, and before publishing it I need to figure...

ragondyn

TypeError: Can't instantiate abstract class Euclidean with abstract methods get_metric, score_pairs

1

File "C:\Project\Self-Similarity-Grouping-master\reid\metric_learning\__init__.py", line 25, in get_metric return __factory[algorithm](*args, **kwargs) TypeError: Can't instantiate abstract class Euclidean with abstract methods get_metric, score_pairs I meet this question in Self-Similarity-Grouping-master\reid\metric_learning\__init__.py line25

zongzhesun

Market2Duke results

13

I runned the code in Market2Duke and Duke2Market, the result of Duke2Market is a match to the reported numbers while the result of Market2Duke has a drop in performance. The...

jh97321

I cannot find the "source_train.py" in this project, where can I find it?

shuxjweb

你好，刚看完论文，还没来及看代码。对SSG+以及SSG++的训练过程，这点有些疑问。SGG+是不是先利用无监督方法将SSG模型完全收敛以后，利用稳定的聚类来选取label参考集，对target上面每个数据取标签然后再去fine-tuneSSG？

talentCODE

YuanXinCherry

Hi, I am reproducing your work, could you please update the code and fix the error? thanks

zzw-zwzhang