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
LambdaResNet Implementation? #23
Comments
Hi! I have no plans as my research interests rests in attention rather than convolutions Feel free to submit a PR though! |
@lucidrains Here is an implementation of Lambda ResNet with training logs and pre-trained models on ImageNet https://github.com/d-li14/lambda.pytorch. Would you please consider adding it to this repo? |
@d-li14 Did your implementation require a lot of memory to train? |
Here is another attempt to integrate lambda-net into a pre-trained model. Work in progress though, https://github.com/innat/LamdaDenseNet-121 |
I have been looking around and found one implementation of LambdaResNets, although there seem to be some metric performance problems and I've found wall-clock performance problems (runs ~7x slower than normal resnets).
Do you plan on putting out a lambdaresnet model in this repository?
The text was updated successfully, but these errors were encountered: