search

AbnerHqC / GaitSet

A flexible, effective and fast cross-view gait recognition network
582 stars 170 forks source link

Less accuracy of OUMVLP dataset while testing... #161

Open kamrulhasanrony opened 2 years ago

kamrulhasanrony commented 2 years ago

I have got a question about training oumvlp dataset. Is less batch size impact accuracy? Due to machine limitations, I ran with a batch size (8,3) and got an accuracy of 84% only... I've done everything as the paper says. What could be the problem??? Thanks in advance.

m2005dh commented 2 years ago

I have got a question about training oumvlp dataset. Is less batch size impact accuracy? Due to machine limitations, I ran with a batch size (8,3) and got an accuracy of 84% only... I've done everything as the paper says. What could be the problem??? Thanks in advance.

hi, I had a problem during running the train, could you help me? when I ran it. the error was : ---------anaconda3\envs\gaitset\lib\site-packages\numpy\core\fromnumeric.py", line 56, in _wrapfunc return getattr(obj, method)(*args, **kwds) ValueError: cannot reshape array of size 230400 into shape (64,64,newaxis)