Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

can't find "create_dataset" this file #39

Closed
hsqaihkl opened this issue Jun 14, 2018 · 5 comments
Closed

can't find "create_dataset" this file #39

hsqaihkl opened this issue Jun 14, 2018 · 5 comments

Comments

@hsqaihkl
Copy link

@huanghoujing hi, I run the train.py but in the 19 lines :“from aligned_reid.dataset import create_dataset”,but i can't find this file in "dataset" .

@huanghoujing
Copy link
Owner

Thank you for your attention! This create_dataset is defined in file aligned_reid/dataset/__init__.py.

@hsqaihkl
Copy link
Author

@huanghoujing
Ok ,I have foud it !
Hi,houjing,I have run it in my project to test it Whether it in a real time ,but I test it and print time ,it use more time in creating the feate, use time 804ms.
my system :1050ti,7700HK,win10 ,cuda9.0 ,cudnn7.1,python3.6, torch0.4
is that my computer too low?

@hsqaihkl
Copy link
Author

this is the creat feat code:

ims_var = Variable(transer_var_tensor(torch.from_numpy(images), self.device_id).float(), volatile=True)
feats,_ = self.model(ims_var)[:2]
feats = feats.data.cpu().numpy()

could you help me to improve it?

@huanghoujing
Copy link
Owner

Your code looks alright. Maybe the speed is determined by the machine.

@hsqaihkl
Copy link
Author

Ok Thks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants