nana

how can i train on other datasets？the performance is bad on other datasets

i can’t understand the positive and negative samples' choosing process,can you describ it more detail

i learn something about LR，i don‘’t understand how the W (sparse coefficient matrix) is learnt. hope your explanation.thank you

thank you very much. i test single dataset with the trained combined model and change the class number to 2220,and the test result of map and cmc1 are low on...

> > i train the model with your code on combined dataset,when i try to test on single dataset,it occurs size mismatch bug > > I think the reason is...

the result of single train single test can almost get the accuracy as the paper said. the problem occurs on combined model .Looking forward to your prompt reply.

if you can share your CUHK-SYSU training data.thank you very much