Cross-Modal-Re-ID-baseline

Cross-Modal-Re-ID-baseline copied to clipboard

Hi， Dr Ye， thanks for your released code. I have trained the model but got lower results ------only 28.03（map）. I just run `python pre_process_sysu.py` to prepare the dataset and 'python...

ssyou

How to test RegDB in infrared to visible test mode？

Shanonshan

Thanks for your impressive work. In the ICCV21 CAJ paper, the grayscale transformation (CA) is used. But is seems that the codes don't use CA? Could you please describe what...

jiangmingbuaa

What about the ablation study of AGW on visible-infrared Re-ID?

1

Hi~ It is a nice job. The proposed WRT loss seems to be the improved version of the original Triplet loss. Did you carry out any ablation studies on the...

mouxingyang

can't understand this code->for epoch in range(start_epoch, 81 - start_epoch):

2

https://github.com/mangye16/Cross-Modal-Re-ID-baseline/blob/910c650fcdda75984dfc9da3d9d46eb044c56969/train.py#L362

Hua-XC

https://github.com/mangye16/Cross-Modal-Re-ID-baseline/blob/910c650fcdda75984dfc9da3d9d46eb044c56969/train.py#L362

CottonCandyZ

Don‘t converge on RegDB

1

Thanks for the source code, it helped me a lot. But when I train on RegDB dataset, the model does not converge. I used the following statement: `python train_ext.py --dataset...

Su-hya

Results cannot be reproduced？

13

I train a model by:  After training 98 epoch, I get the following results:  Why my result are so different from yours?  The setting is: 

cq0907

Update model.py

1

First of all, thank you for providing this code as a benchmark method for the VI-ReID task. During the experiment, I found a serious problem in the Non-Local module. The...

workingcoder

请问如何该看到可视化界面呢？

1

zhangzhang1524