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

Resnet-101 pretrained model on Visual Genome #154

Open
aelnouby opened this issue May 3, 2018 · 7 comments
Open

Resnet-101 pretrained model on Visual Genome #154

aelnouby opened this issue May 3, 2018 · 7 comments

Comments

@aelnouby
Copy link

aelnouby commented May 3, 2018

Hi @jwyang ,

Thanks for this project. I am wondering if you can share the pre-trained model using Resnet-101 and the bottom-up attention preprocessing, you mentioned here that you were able to get 10 mAP.

If the pretrained model is not available, could you share the hyperparams you used and the time per epoch.

Thanks.

@jwyang
Copy link
Owner

jwyang commented Jun 29, 2018

@aelnouby Hi, I will train the model and put the pre-trained on this repository soon

@erobic
Copy link

erobic commented Aug 28, 2018

Is the pre-trained model available now?

@yzhq97
Copy link

yzhq97 commented Jan 30, 2019

@jwyang Thanks for this project. I am also doing a relevant research and would appreciate if you provide the 1600-class VG model which achieved 10 mAP. Thanks!

@LuoweiZhou
Copy link

+1. Thanks!

@alibabadoufu
Copy link

Hi, may I know if anyone has the pretrained model? (Resnet 101 on Visual Genome)

@nilinykh
Copy link

Hello, also curious if it is is possible to get the pre-trained VisGen model, which achieved 10 mAP.

@dreamedrainbow
Copy link

Still Wondering

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

8 participants