search

layumi / AICIty-reID-2020

:red_car: The 1st Place Submission to AICity Challenge 2020 re-id track (Baidu-UTS submission)
MIT License
449 stars 110 forks source link

ff = torch.FloatTensor(n,512).zero_().cuda() #38

Closed vokhidovhusan closed 2 years ago

vokhidovhusan commented 3 years ago

Hi @layumi sorry for bothering you. May I ask you again?

def extract_feature(/*...*/):    
   // ...
    for data in tqdm(dataloaders):
        //...
        ff = torch.FloatTensor(n,512).zero_().cuda()

Where did 512 come from ? I am curious about the reason why you set the parameter as 512.

layumi commented 3 years ago

Hi @martianvenusian , It is the dimension of the feature before the classification layer. https://github.com/layumi/AICIty-reID-2020/blob/master/pytorch/model.py#L43