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

Pre-trained checkpoints and features on MODEL_ZOO/FEATURES_ZOO missing #9

Open
beasteers opened this issue Feb 15, 2023 · 3 comments
Open

Comments

@beasteers
Copy link

beasteers commented Feb 15, 2023

It looks like none of the links in the model/feature zoo pages link to anything. Do you have a plan to release them?

UPDATE: are these them? https://github.com/alibaba/EssentialMC2/blob/main/MODEL_ZOO.md

@wangxiang1230
Copy link
Contributor

It looks like none of the links in the model/feature zoo pages link to anything. Do you have a plan to release them?

UPDATE: are these them? https://github.com/alibaba/EssentialMC2/blob/main/MODEL_ZOO.md

Sorry for the late reply. Our HyRSM is based on ImageNet pretrained ResNet-50, and the code can load the pre-trained model. Because of the lengthy and complicated approval process, our checkpoints are not open source. Feel free to contact me if you have any issues while reproducing.

@phoenix98Glitch
Copy link

Hey are the checkpoints available now? I click on the link and it directs me back to the homepage. Am I missing something here?

@wangxiang1230
Copy link
Contributor

Hey are the checkpoints available now? I click on the link and it directs me back to the homepage. Am I missing something here?

Hi, thanks for your attention. Due to the lengthy company approval process for open source model training weights, we did not open source training checkpoints, you can run our code to train your own model, the code will automatically download the image net pre-trained ResNet50 model.

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

3 participants