Richard Abrich

https://aws.amazon.com/blogs/compute/uploading-to-amazon-s3-directly-from-a-web-or-mobile-application/ Looks like we can get away with a lambda function. I think this should be configured in the same script that configures the s3 bucket. Follow the pattern in...

I think we want something like: ``` python -m openadapt.finetune --recording_id --model ```

@bi-loop any interest? 🙏

https://chatgpt.com/share/e92a6524-bb9a-4692-ac2e-9e10fe52aeff For now we will focus on reducing the number of segments per prompt in upstream logic.

A regression was introduced in https://github.com/OpenAdaptAI/OpenAdapt/pull/679 in `openadapt/adapters/ultralytics.py`. Before: ``` conf: float = 0.4, iou: float = 0.9, ``` After: ``` # threshold below which boxes will be filtered out...

The regression has been fixed in https://github.com/OpenAdaptAI/OpenAdapt/pull/758 but the issue will crop up again for lower NMS threshold values.

😅

Sounds good @kernel-loophole ! Please DM me on Discord 🙏

Hi @kernel-loophole , thank you for your interest. Can you please be more precise? e.g. where will you implement textgrad? How will you evaluate whether the implementation has been successful?

As part of fixing this, please also add a test 🙏