Dispersion-based-Clustering
Dispersion-based-Clustering copied to clipboard
The source code for our work "Towards better Validity: Dispersion based Clustering for unsupervised Person Re-identification"
Create dataloader for Testing with batch_size 1 Begin to extract features... Process finished with exit code 137 运行mars数据集出错,能帮我看一下吗?谢谢!
Hello, thank you for your great work. I have benefited a lot from it. I'm a beginner in computer vision and person identification. There are many things I don't understand...
Why you don't use the penalized linkages in the code below? Is it a typo/bug since you tried your code with no linkage? https://github.com/gddingcs/Dispersion-based-Clustering/blob/63a0c5294c039ddab18e7f90212de5f3ea17fe3e/reid/bottom_up.py#L310-L311
Hello, I set hyper-parameters 0.1 for size_penalty ,0.05 for merge_percent and 16 for batchSize in your code. But on DukeMTMC-VideoReID, the highest rank-1 is 59.3% and the heighest mAP is...