batch-dropblock-network

batch-dropblock-network copied to clipboard

Hello, I successfully executed this program, but I have some questions about the allocation of datasets. Under normal circumstances, the training dataset and the validation dataset are carried out together....

sksksk1748

数据处理

2

你好，请问是不是不管是哪个数据集，都是用data_manager的class Market1501来处理，只需要更换config里的dataset即可，其他均不变。

wujunyi627

test的逻辑疑问

4

#part branch x = self.res_part2(x) x = self.batch_crop(x) triplet_feature = self.part_maxpool(x).squeeze() 楼主，你好，上述代码是您part分支进行batch drop的操作，我想问下在测试过程中为什么也要进行此操作？而当我在测试代码中去掉此操作时，他的结果和使用是完全一样的，请您指导一下，期待您的回复！！！！

yukaizhou

test

5

when I test, there is a error, ValueError: expected 2D or 3D input (got 1D input), please tell me how should I do.

chj1933

zaiweijian

class activation map

2

Hello, after reading through your dissertation, I saw the class activation map, but I do n’t know how to get it, can you share this visual code? Thank you very...

VIRC-lab-csust

when using eval_func_gpu,list named results is always none

decajcd

lhc11171552

There are "mgn_model" and " mgn_part" in your training log, but i can't find them in the config.py.

GuoGuoYao

Thanks for opening your code . I meet some issues when I train my own data by triplet loss . shape dist_mat : 64*64 N:64 shape '[N, -1]' is invalid...

swpucl