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

where can I download the weight file? #2

Open
zhang11wu4 opened this issue Feb 2, 2018 · 5 comments
Open

where can I download the weight file? #2

zhang11wu4 opened this issue Feb 2, 2018 · 5 comments

Comments

@zhang11wu4
Copy link

hi,
I searched for the whole project but can't find the weight file. Could you pls tell me where can I download the file, thanks.

@xshalan
Copy link

xshalan commented Feb 10, 2018

I can't find it too !

@wyfsh
Copy link
Owner

wyfsh commented Mar 3, 2018

@zhang11wu4 You should download the pre-trained weights from the Darknet project website, and then use the cfg files to train YOLO-LISA model.

@wyfsh wyfsh mentioned this issue Oct 11, 2018
@zhji2822
Copy link

zhji2822 commented Dec 26, 2018

@wyfsh Hello Yifan Wang, can you provide more information about which weight you downloaded? In the note.txt I saw some code number for the download of the weights. However, I was confused what did the number represent.. I just downloaded the weight of tiny-yolo for now. but I don't know which original model weights did you download. Thank you

@wyfsh
Copy link
Owner

wyfsh commented Dec 26, 2018

@zhji2822 This one darknet19_448.conv.23 from YOLOv2. You can read the chapter 'Training YOLO on VOC' from that page. However, YOLOv3 has been already born, so I guess using the new model and network will be better (and it should be :).

@zhji2822
Copy link

zhji2822 commented Dec 26, 2018

Thank you!! I will check it out now, but I am still getting stuck on the problem of the transfer the format of the dataset. Would you mind helping me to figure out that? Thank you a lot!! I have opened a new issue.

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

4 participants