STAR-FC
STAR-FC copied to clipboard
sstzal
The implementation of the CVPR2021 paper "Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes"
Hi, thank for repo. when I run :python test_final.py Traceback (most recent call last): File "STAR-FC/test_final.py", line 4, in from evaluation.evaluate import evaluate File "STAR-FC/evaluation/__init__.py", line 5, in from .evaluate...
关于 实验结果
作者您好，请问论文中的实验结果可以用您在论文中设置的超参数复现出来吗，我这边使用了您在论文中提到的超参数设置（近邻簇为1500中取1300个，并进行90%的节点抽样，use_Sim = True，阈值设置为0，knn设置为80），训练到第一个epoch的3899batch，训练loss降为0.02左右，但在测试集上的pairwise ave_pre很低，不明白为什么？谢谢~
1.Add support to uncontinous label ids 2.Reformat code Signed-off-by: wangyunhang
Recently, when I trained and tested STAR-FC, I got very low BCUBed scores on tests where I achieved PairWise test scores similar to those in the paper...anyone else experiencing the...
Wonderful work! How should I train with the WebFace42M dataset, please? Is there any relevant data with pre-extracted features?