search

mangye16 / Cross-Modal-Re-ID-baseline

Pytorch Code for Cross-Modality Person Re-Identification (Visible Thermal/Infrared Re-ID)
MIT License
336 stars 71 forks source link

What is your python version #3

Closed liurongfang closed 4 years ago

liurongfang commented 5 years ago

Hello,thanks for your beautiful work! but I get some error as follow in run your code: "result = unpickler.load() UnicodeDecodeError: 'ascii' codec can't decode byte 0xaf in position 0: ordinal not in range(128)" maybe is beacause of python version,I use Python 3.6 and Pytorch 1.0.1(stable) with CUDA 10. wait your reply,thanks

mangye16 commented 5 years ago

hi, my python version is 2.7, pytorch is 0.4 and cuda 8.0.

I think you can easily fix the errors with some minor modifications. Good luck!

liurongfang commented 5 years ago

hi, my python version is 2.7, pytorch is 0.4 and cuda 8.0.

I think you can easily fix the errors with some minor modifications. Good luck!

Thank you!I am run through this in python 2.7,pytorch 1.0.1 and cuda 8.0,it's ok,good work:).But maybe this code just implement ID loss as a baseline,not all details in paper?and I reading another code(Visble-Thermal-Person-Re-Identification).