Yixiao Ge

> "rerank_dist = compute_jaccard_distance(target_features, k1=args.k1, k2=args.k2, search_option=3, use_float16=True" > It's a pity that it does not work. A server with 384G memory is still facing the pointed error when the...

One potential solution is to use `cuml`(https://github.com/rapidsai/cuml) instead of `sklearn` package (I have tried to cluster over 1 million data with `cuml`.). However, `cuml` does not support the pre-computed affinity...

Please double check the arg `--resume`, which directs the absolute path for `best_net_E.pth.tar`.

It actually produces the sample inside 25m and is used for evaluation. It cannot be deleted.

First, as I remember, `select` here does not store the positive samples inside 10m, instead, it is just used for **sampling** valid query images. Second, `train_neg` stores the images **inside**...

It seems that you use the same data samples on the target domain for both unsupervised training and testing. I am confused about it. Look forward to your reply. Thanks!

Hi all, I have accelerated the reranking process, please refer to `def compute_jaccard_dist(...)` in [MMT/mmt/utils/rerank.py](https://github.com/yxgeee/MMT/blob/master/mmt/utils/rerank.py#L106). The function is plug-and-play in this SSG repo, i.e. `input_feature, input_feature_source` in [SSG/reid/rerank.py](https://github.com/OasisYang/SSG/blob/master/reid/rerank.py#L27) is the...

@bashar-tom Hi, have you solved this issue? I also met this problem. Thanks!

I achieved the performance of ``` Recall Scores: top-1 86.1% top-5 93.0% top-10 95.0% ``` by training from conv3 of vgg16 with learning rate of 0.0001 and applying PCA+whitening followed...

> I achieved the performance of > > ``` > Recall Scores: > top-1 86.1% > top-5 93.0% > top-10 95.0% > ``` > > by training from conv3 of...