Traceback (most recent call last): File "test_final.py", line 167, in gt_labels = np.load('./pretrained_model/gt_labels.npy') File "/mnt/lustre/caoguoliang1/anaconda3/envs/cluster/lib/python3.6/site-packages/numpy/lib/npyio.py", line 416, in load fid = stack.enter_context(open(os_fspath(file), "rb")) FileNotFoundError: [Errno 2] No such file or directory: './pretrained_model/gt_labels.npy'

What is gt_labels.npy?

I test ms1m part1_test.bin with the model you provided. The result: [Time] evaluate with pairwise consumes 0.0512 s ave_pre: 0.9559, ave_rec: 0.8870, fscore: 0.9202 [Time] evaluate with bcubed consumes 20.8486 s ave_pre: 0.0858, ave_rec: 1.0000, fscore: 0.1581 [Time] evaluate with nmi consumes 0.1714 s nmi: 0.9738

Hi, I have trained and tested star-fc with public person datasets MSMT and Market, but got very poor results. Could you tell me why?

2022-03-18 18:18:19.397 real clusters: 3060, predict clusters: 7993

2022-03-18 18:18:19.397 [Time] evaluate with pairwise consumes 0.0095 s

2022-03-18 18:18:19.397 ave_pre: 0.0032, ave_rec: 0.8302, fscore: 0.0064

2022-03-18 18:18:19.397 [Time] evaluate with bcubed consumes 4.2473 s

2022-03-18 18:18:19.397 ave_pre: 0.4681, ave_rec: 0.8321, fscore: 0.5991

2022-03-18 18:18:19.397 [Time] evaluate with nmi consumes 0.0290 s

2022-03-18 18:18:19.397 nmi: 0.7601

2022-03-18 18:18:19.397 avg_acc: 0.8054215519079088

2022-03-18 18:18:19.397 pairwise: 0.006409889997558421

2022-03-18 18:18:19.397 bcubed: 0.5991425302360325

2022-03-18 18:18:19.397 nmi: 0.7600691590384783

Very good job ! I want to know if the author can release WebFace42M's feature file and its train/test splits. So that more researchers can follow and cite this work.

Hi, I followed your example, didn't change the parameters, just replaced the dataset, and then I was reminded that the number of samples is too large, how can I fix it?

Hi! I am checking the train_gcn.py and noticed something weird. In line 32 def perform_val() the test_inst_num is defined as the length of test_idx2lb, which is the total number of samples in the test set. However, the pair_a and pair_b are defined as lists of k duplicates of each sample and their k nearest neighbors. When looping over the patches, the patch_size is defined as patch_size = int(test_int_num/patch_num). It seems the loop only covers a total of sample size, instead of k times of the sample size, which is the total number of pairs. Does this mean only the initial portions of pair_a and pair_b are evaluated? The average_acc is also obtained by dividing sum_acc and test_inst_num, which is only a portion of pair a and pair b. Another question is why only test the pair-wise accuracy on the knn pairs instead of all pairs? The knn pairs are selected since they are close to each other, won't this cause bias since they are very likely to from the same cluster?

Congratulations on your publication! I am reading your code and paper, however, I have a question about the sampling policy. In your paper, you mentioned M = 2, and N = 750, so two seeds, and their nearest 750 clusters are selected before CR, which makes a total of 1500. However, in train_gcn.py line 146, the for batch in range(cls_num): it seems all the clusters are looped, and for each of them, a total of 1300+200 = 1500 clusters are sampled before CR. In every training step, the features from these clusters are used to construct the affinity graph after SR. Did I miss something?

In Table 4, the inference time of starfc is 310s, which is faster than GCN-V+E 609s. But did you compare the inference time between starfc and gcnv (without gcn-e part)? Which one is faster? In my experiments, the accuracy of GCN-V is high enough. And the inference time of GCN-E takes up most of the inference time of GCN-V+E. So in most scenarios, GCN-E is not needed.

Hi ,congratulations to your work! Got some questions , maybe you could help? Thanks!

1. What is cfg.cluster_num ?
2. Is it the N in paper's Algorithms 1?
3. Why added by 200 in train_gcn.py line 143

because the code will build knn in faiss(cpu mode), we change the config "knn_method = faiss" to "knn_method = faiss_gpu", then runing with error

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 import evaluate File "STAR-FC/evaluation/evaluate.py", line 9, in from utils import Timer, TextColors File "STAR-FC/utils/init.py", line 5, in from .knn import * File "STAR-FC/utils/knn.py", line 409, in class knn_faiss_dynamic(knn_dynamic): NameError: name 'knn_dynamic' is not defined

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~