salamander

I love AI. QA, Data Analyst @AmazonJP My tweets are my own and not the views of my employer.

[TensorFlow @TensorFlow]

Get ready for #TFDevSummit ⏰

Tune in to the livestream tomorrow 3/11 at 9:00a PT

https://t.co/m3ZXrGp2Ko

[salamander @salamander_jp]

@fagai おめでとーヽ(・∀・)ノ🎉
恒例のしました！お楽しみに！（ ＞ω＜ ）

[salamander @salamander_jp]

@maxmellon_9039 おめでとうございます！🍜🎉

[TensorFlow @TensorFlow]

BodyPix 2.0 has been released, including multi-person segmentation support and a new live demo!

To learn more, read the post by @tylerzhu3, @oveddan, @greenbeandou, @dsmilkov, @karlssonper, @ire_alva, @nsthorat.

Details here → https://t.co/Zq8dwiNO5A

[Quoc Le @quocleix]

Want to improve accuracy and robustness of your model? Use unlabeled data!

Our new work uses self-training on unlabeled data to achieve 87.4% top-1 on ImageNet, 1% better than SOTA. Huge gains are seen on harder benchmarks (ImageNet-A, C and P).

Link: https://t.co/ZYDaef6sdp

[Jian Tang @tangjianpku]

We released the code of our NeurIPS'19 paper "Probabilistic Logic Neural Networks for Reasoning", which combines traditional Markov Logic Network (symbolic reasoning) and Knowledge Graph Embedding (Continuous reasoning) for reasoning on knowledge graphs.(https://t.co/XOuUWyoXfX)

[Rithesh Kumar @ritheshkumar_]

Happy to finally announce our work (from @LyrebirdAi and @MILAMontreal) : MelGAN - GANs for conditional waveform synthesis https://t.co/HAhfHcC9jH . MelGAN is the first pure GAN-based model for raw audio synthesis not requiring distillation from a teacher autoregressive model.

[Chelsea Finn @chelseabfinn]

Tired of your robot learning from scratch? We introduce RoboNet: a dataset that enables fine-tuning to new views, new envs, & entirely new robot platforms.
https://t.co/yU7QQF1gnq
https://t.co/5yHf53BnyV

w/ Dasari @febert8888 Tian @SurajNair_1 Bucher Schmeckpeper Singh @svlevine

[Rui Shu @_smileyball]

New paper on disentanglement c: Given the recent impossibility results in unsupervised disentanglement, we decided to be optimistic and instead provide guarantees (unimpossibility results?) via weak supervision (1/13)
https://t.co/og5j21CQaw
https://t.co/raabrb5cbY

[Roberto @RobobertoMM]

We present 6-PACK, an RGB-D category-level 6D pose tracker that generalizes between instances of classes based on a set of anchors and keypoints. No 3D models required! Code+Paper: https://t.co/Q5njNUawbz w/ Chen Wang @danfei_xu Jun Lv @cewu_lu @silviocinguetta @drfeifei @yukez

[Sergey Levine @svlevine]

RoboNet: a new large-scale dataset collected across multiple robots, labs, viewpoints, and objects, for studying generalization of predictive models and controllers across different robots!

https://t.co/si42INu3gj
https://t.co/RGlNrsMWBi

video:
https://t.co/KxtoYZKJLA

[salamander @salamander_jp]

本日の資料です。https://t.co/rgWVvoGEzU #kng8

[salamander @salamander_jp]

GitHub Actions Meetup Osaka #1 を公開しました！ https://t.co/UliWudYQF3 #GitHubActions

[Markus Schütz @m_schuetz]

"Progressive Real-Time Rendering of One Billion Points Without Hierarchical Acceleration Structures"

Code: https://t.co/qMXNRv7JkW
Paper: https://t.co/D9qi3GMIgy

Video: https://t.co/qhlT1tMajC
Previous V.: https://t.co/8rTIsK9koB

Using C++, Javascript (@v8js ), OpenGL, #lidar

[Google DeepMind @GoogleDeepMind]

In our new work, we propose a framework for humans teaching robots to accomplish tasks using visual inputs:
https://t.co/7NBma4k3GI
https://t.co/RGAJ9l9yYc

[GitHub @github]

Calling all machine learning developers and data scientists 👀

Today we're excited to share the CodeSearchNet Challenge and the release of a large dataset for natural language processing and machine learning.
https://t.co/kXDH4FRqhq

[salamander @salamander_jp]

repository_dispatch イベントはいいぞ！
https://t.co/XI98rMP9Pn
#GitHubActions

[salamander @salamander_jp]

どこでActionsを実行?
https://t.co/L0Wmhw4AOO
#GitHubActions