search

KovenYu / MAR

Pytorch code for our CVPR'19 (oral) work: Unsupervised person re-identification by soft multilabel learning
https://kovenyu.com/publication/2019-cvpr-mar/
315 stars 83 forks source link

MSMT17.mat can't read #25

Closed QingzeYin closed 4 years ago

QingzeYin commented 5 years ago

I use python command to run this code. But 'Input/output error' was shown immediately, which said:

OSError: Can't read data (file read failed: time = Thu Oct 3 13:19:29 2019 , filename = 'data/MSMT17.mat', file descriptor = 6, errno = 5, error message = 'Input/output error', buf = 0x5629561acaa0, total read size = 3656, bytes this sub-read = 3656, bytes actually read = 18446744073709551615, offset = 6684483979)

Is there some problem with data MSMT17.mat? Cause I re-download this and tried for three times but also obtain same error annotation.

Could you please give me some suggestions or clues to solve that? Truly thanks!

KovenYu commented 5 years ago

Sorry currently I'm away from our lab and for a widely known reason I cannot use VPN to access our server. So for this specific problem I can barely help (it is weird, though, as other people have not observed similar problems). I would suggest you might download the original image dataset and format it by /data/construct_dataset_MSMT17.m.

QingzeYin commented 5 years ago

Sorry currently I'm away from our lab and for a widely known reason I cannot use VPN to access our server. So for this specific problem I can barely help (it is weird, though, as other people have not observed similar problems). I would suggest you might download the original image dataset and format it by /data/construct_dataset_MSMT17.m.

Thanks for replying!

Do you think is the problem with _/data/construct_datasetMSMT17.m? Or with MSMT17.mat? Do I need to download original MSMT17 dataset to do pre-train again? Actually I am confused about whether can use your pre-trained model to reproduce.