News for hackers. Stuff that matters.
Re:Announcing YouTube-8M: A Large and Diverse Labeled Video ... by iverjo on Wednesday September 28, 2016 @05:55PM (#12601664)
This is nice :) Kudos to the Youtube guys for releasing this. I'm a data scientist in a startup where one of the things I do is create multi-label models for classifying YouTube videos. My current model has 90 % precision and 69 % recall, while Youtube-8M has 78 % precision and 14 % recall, with respect to the human raters. I guess one of the reasons is that my model only has around 100 categories, while Youtube-8M has 4800. It's like comparing apples with pears, but still interesting.
Re:Announcing YouTube-8M: A Large and Diverse Labeled Video ... by tiplus on Thursday September 29, 2016 @07:41AM (#12604513)
Sounds interesting, do you guys have a blog at mashtime? What kind of hardware/software do you use for training? Tensorflow? on AWS or bare metal GPUs?
Re:Announcing YouTube-8M: A Large and Diverse Labeled Video ... by iverjo on Thursday September 29, 2016 @08:43AM (#12604785)
We don't have a blog yet. We're using Azure for the hardware and mainly scikit-learn for the training (we train only on metadata at the moment). Will probably start using Tensorflow soon.
Re:Announcing YouTube-8M: A Large and Diverse Labeled Video ... by doozler on Friday September 30, 2016 @07:34AM (#12611833)
Would you say Tensorflow is a good way to get started with Machine learning?
Re:Announcing YouTube-8M: A Large and Diverse Labeled Video ... by iverjo on Sunday October 02, 2016 @03:39PM (#12623864)
I'd say scikit-learn is a better way to get started with machine learning. Check this out, for example: https://www.youtube.com/watch?v=cKxRvEZd3Mw