Hacker News Reader

npRandomon Launch HN: Activeloop (YC S18) – Data lake for deep learning

Full Disclosure: I'm a ML Team Lead at DagsHub.

TL;DR DagsHub lets you stream datasets from any repo you can access for free. We have open-source datasets for various tasks and domains (image, video, MRI, audio, etc.) that you can use, or upload yours and stream it. Learn more - https://dagshub.com/docs/feature_guide/direct_data_access/

How does it work? Every DagsHub repo comes with a configured remote storage, where users can host models, datasets, or any other large file.

We recently added a new capability to our open-source client and free-to-use API that enables the streaming of files stored on DagsHub Storage.

It enables access to any dataset stored on DagsHub, stream it to your machine, version it, and upload it to your DagsHub repo - all from your python code.

I think the coolest part of this feature is that it doesn't require any modifications to your code base or data format.

You can find more info about it here -> https://dagshub.com/docs/feature_guide/direct_data_access/

Feel free to reach out if you have any other questions (:

npRandomon YOLOv6: Redefine state-of-the-art for object detection

I compared YOLOv5 and v6 on several images, and v6 outperformed v5 by ~10% in the confidence level of the labels.

npRandomon YOLOv6: Redefine state-of-the-art for object detection

Yup. They don't plan to release a paper but a technical report https://github.com/meituan/YOLOv6/issues/95

npRandomon YOLOv6: Redefine state-of-the-art for object detection

I agree. The name YOLO is heavily amused (A good example: https://github.com/jinfagang/yolov7). However, you should note that the research team of YOLOv5 is also not the original one. As @garblegarble mentioned, the original research group stopped working on it (https://news.ycombinator.com/item?id=31918087).