Nice work and the accompanying library/codebase for model-parallelism in PyTorch looks really sweet!
— Thomas Wolf (@Thom_Wolf) February 11, 2020
👉 https://t.co/yqzaf5glBa https://t.co/sg4igQV6xI
Nice work and the accompanying library/codebase for model-parallelism in PyTorch looks really sweet!
— Thomas Wolf (@Thom_Wolf) February 11, 2020
👉 https://t.co/yqzaf5glBa https://t.co/sg4igQV6xI
"PyTorch is by a very slim margin faster than TensorFlow 2.0 [...] when you run TensorFlow in non-Eager mode. [...] since Eager mode is now enabled by default in TensorFlow 2.0; PyTorch is significantly faster." ->Prep for a seminar, anyone has benchmarks?https://t.co/agRL3tDY4k
— Sebastian Raschka (@rasbt) February 9, 2020
We just released PyTorch3D, a new toolkit for researchers and engineers that’s fast and modular for 3D deep learning research: https://t.co/RmMSXJoWCm pic.twitter.com/H75Ai9gH2I
— Facebook AI (@facebookai) February 6, 2020
Hydra provides an ability to compose and override configuration from the command line and config files, helping PyTorch developers to more easily manage complex ML projects. https://t.co/Kftd5mwp2E
— PyTorch (@PyTorch) February 5, 2020
How did I not know of this until now?https://t.co/qXTEbPpFMx pic.twitter.com/vgwvszgFEo
— Jeremy Howard (@jeremyphoward) February 4, 2020
New models from:
— Julien Chaumond (@julien_c) February 3, 2020
- @Wietsedv (Dutch BERT),
- @douwekiela at Facebook AI (MMBT, multi-modal model)
- @formiel, @laurent_besacie et al. (FlauBERT, French-trained XLM-like)
- @loretoparisi, @simofrancia et al. at @musixmatch (UmBERTo, Italian CamemBERT-like) pic.twitter.com/qgJ0fwqiwC
Given that data loading can be a major bottleneck in many DL projects, this sounds like an interesting project to check out: "Accelerating Pytorch with Nvidia DALI" --> "on small models it's ~4X faster than the Pytorch dataloader" https://t.co/W11D2OPCFf
— Sebastian Raschka (@rasbt) February 3, 2020
OpenAI Switches to PyTorch https://t.co/A1mZX0lpgZ
— /MachineLearning (@slashML) January 30, 2020
Kornia is a GPU accelerated computer vision library for @PyTorch.
— Jeremy Howard (@jeremyphoward) January 27, 2020
Link: https://t.co/XwrPrBczIY https://t.co/HMRNNcOQTj
If you want to learn about privacy-preserving machine learning, then there is no better resource than this step-by-step notebook tutorial by @iamtrask.
— Sebastian Ruder (@seb_ruder) January 26, 2020
From the basics of private deep learning to building secure ML classifiers using PyTorch & PySyft.https://t.co/Fg0il4ZnUH
The Autonomous Learning Library: A PyTorch Library for Building Reinforcement Learning Agents https://t.co/VbCAhcFJJ7
— /MachineLearning (@slashML) January 20, 2020
Fast and reliable face detection with RetinaFace.PyTorch https://t.co/hVUxz4FXRJ #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) January 16, 2020