HackerTrans
TopNewTrendsCommentsPastAskShowJobs

npRandom

no profile record

Submissions

Why You Should Care About the EU AI Act Today

pub.towardsai.net
1 points·by npRandom·3 tahun yang lalu·0 comments

Point-E – OpenAI's Model to Generate 3D Point Clouds from Prompts

dagshub.com
3 points·by npRandom·4 tahun yang lalu·1 comments

TikTok published an article on their recommendation system architecture

arxiv.org
3 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

Code as Policies: Robots that write their own code

arxiv.org
1 points·by npRandom·4 tahun yang lalu·0 comments

Show HN: New open source EDA tool

github.com
1 points·by npRandom·4 tahun yang lalu·0 comments

Show HN: I used streaming to skip downloading my 45GB dataset

github.com
31 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

[untitled]

1 points·by npRandom·4 tahun yang lalu·0 comments

YOLOv6: Interactive Object Detection Demo

yolov6.dagshubusercontent.com
6 points·by npRandom·4 tahun yang lalu·2 comments

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

dagshub.com
138 points·by npRandom·4 tahun yang lalu·61 comments

YOLOv6: state-of-the-art object detection at 1242 FPS

dagshub.com
11 points·by npRandom·4 tahun yang lalu·0 comments

comments

npRandom
·4 tahun yang lalu·discuss
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 (:
npRandom
·4 tahun yang lalu·discuss
I compared YOLOv5 and v6 on several images, and v6 outperformed v5 by ~10% in the confidence level of the labels.
npRandom
·4 tahun yang lalu·discuss
Yup. They don't plan to release a paper but a technical report https://github.com/meituan/YOLOv6/issues/95
npRandom
·4 tahun yang lalu·discuss
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).