binaryzeitgeist
binaryzeitgeist on Hacker News
Re:Self-Supervised Video Object Segmentation by Motion Grouping
on Saturday April 17, 2021 @03:07AM (#26842238)
This is very similar to work by Curious AI done a couple years ago, although it didn't work on high res videos.
Tagger: Deep Unsupervised Perceptual Grouping
Re:California sues Cisco alleging discrimination based on India’s cast...
on Friday July 10, 2020 @11:40PM (#23799272)
This is rich coming from a state that introduced a bill like ACA-5.
Re:NVIDIA GeForce driver deployment in datacenters is forbidden now
on Monday December 25, 2017 @01:43AM (#16003044)
Here you go: https://github.com/tensorflow/tensorflow/issues/22
Re:NVIDIA GeForce driver deployment in datacenters is forbidden now
on Monday December 25, 2017 @01:23AM (#16002988)
What surprised me in the first place is why Tensorflow an "OpenSource" initiative by Google chose proprietary CUDA over "OpenSource" OpenCL.
Check Tensorflow issue 22 for more info.
Just sayin.
Re:NVIDIA GeForce driver deployment in datacenters is forbidden now
on Monday December 25, 2017 @01:21AM (#16002982)
[Merry Xmas Nvidia! - Torvalds](https://4bds6hergc-flywheel.netdna-ssl.com/wp-content/upload...)
Re:Hardware Architectures for Deep Neural Networks [pdf]
on Wednesday September 06, 2017 @10:58AM (#15184178)
290 image-heavy pages. smh
Re:Caffe2: Open Source Cross-Platform Machine Learning Tools
on Wednesday April 19, 2017 @05:43AM (#14146575)
When are you planning to release the Mask-RCNN code?
I'm trying to implement the RoIAlign layer in Tensorflow and I've a few doubts and having the author's code would definitely help in implementing it.
Re:High-performance employees need quieter work spaces
on Wednesday March 22, 2017 @12:30PM (#13932275)
No Shit, Sherlock !
Re:Most scientists 'can't replicate studies by their peers'
on Thursday February 23, 2017 @11:51AM (#13715350)
Specifically to the CS context, I think some version of double blinded peer code-review should be made mandatory for a publication.
I've seen authors skip quite a many details that are quintessential to the replication process.
In short, if research is not replicable by the peer community it just useless, that's what it is.