-
I was wondering which version of cv2 and python3.7 are you using? I tried python3.7.7 and it gives some unexpected errors when installing other required packages like yacs. Thank you!
-
你好，我在训练 PartialReID 的时候，提示没有 compute_dsr_dist 和 reid_losses 这两个定义，通过全局搜索也没有找到
compute_dsr_dist == get_dsr_dist ??
reid_losses 在以前版本找到了，修改后运行如下命令，会出现 config配置错误
CUDA_VISIBLE_DEVICES='1' python p…
-
我写了PRETRAIN_PATH但是好像没有用到。我这边训练market1501上top1只有93.6，不知道是不是没有载入预训练模型的原因
-
Hi，Thanks for this great work!
I'd like to reproduce your results with ResNet50 using AugMix feature.
Could you sharing the training hyperparameters?
Besides, any data augmentation usage recommenda…
-
Hi Liao,
Thanks for your awesome implementation.
I met some problem when trying to reproduce the result showed in your model_zoo
e.g.
As for market1501, strictly follow your step without any modi…
-
Hi, @L1aoXingyu ,
First, very appreciate for your excellent reid sota work.^_^. I am very interested in this project.
I have tried the two SBS(R50) models on dataset market1501. But I do not get the…
-
Hi Author I am a college student studying deep learning in Korea. I read your paper very interesting. But I am running AugMix on imagenet and I have to wait 6 days with my GPU machine. So I'm wonderin…
-
Do you have any suggestions to run the strongerbasline? Currently I am using the default params in configs/Market1501/sbs_R50.yml for training and the loss is extremely large. The test accuracy is als…
-
Hi, not an issue per-se but just wondering if this information is tracked anywhere? I couldn't find any baselines in the original paper. Is it fair to say that 76.9% test acc from https://arxiv.org/ab…
-
I'm having trouble achieving decent ImageNet results with the mixing + JSD loss. Are the hparams in the `imagenet.py` script what was used for paper results, was the same code used for the paper?
…