Lucas Liebenwein

Hi, Thanks for raising this issue. That's a great idea! It should be really easy to implement since all the checkpoints are handled by the trainer [here](https://github.com/lucaslie/torchprune/blob/0932cbc3c1611fe9956cd9a79f55c411068c90b8/src/torchprune/torchprune/util/train.py#L799). I will implement...

Hi, thank you for your interest! I would recommend checking out the [README here](https://github.com/lucaslie/torchprune/blob/main/src/torchprune/README.md). It should contain all the info to add your own CNN models. :)

Hi, thanks for the interest in our paper. I am currently working on the release and will keep you posted as soon I will released it. Thank you, Lucas

Hi, thanks for reaching out. here is an overview and please feel free to ask me any follow-up questions if you want to go into details about any of those:...

This is currently not supported and/or I don't have plans to support it. If you are interested in inference time speed-ups, then I would recommend writing some type of post-processing...

Thanks for getting in touch. I am using pydantic to validate a user-provided config. So my main motivation is to have a simple overview with field names and default values...