Tag: pytorch

PyText will be open sourced by @fb_engineering later this month, allows rapid prototyping and production deployment of @PyTorch NLP models pic.twitter.com/OU2meSlN86

— Peter Skomoroch (@peteskomoroch) October 2, 2018

Old process: PyTorch ➡️ ONNX ➡️ Caffe2
New process: PyTorch v1.0

Bill Jia #PyTorchDevConf pic.twitter.com/WJTyT5LyJl

— Rachel Thomas (@math_rachel) October 2, 2018

Fastai v1 is now officially live. First library to provide a unified and simple API for applying DL to vision, text, tabular data and collaborative filtering. Be sure to check out the docs: https://t.co/tWLGlj28V6

— Sylvain Gugger (@GuggerSylvain) October 2, 2018

After 2 years of development, we've just launched fastai v1, the first deep learning library with a simple consistent API across vision, text, tabular, and collaborative filtering data. Built on the wonderful @PyTorch v1 (preview released today)https://t.co/6tFYNkvF8v pic.twitter.com/p2TytMckx5

— Jeremy Howard (@jeremyphoward) October 2, 2018

Excited about the release of fastai v1! fastai is the 1st deep learning library to provide a single consistent (& state-of-the-art) interface to:
- vision
- text
- tabular data
- time series
- collaborative filteringhttps://t.co/shHEz1tEsR

— Rachel Thomas (@math_rachel) October 2, 2018

Corrected link: https://t.co/zzxhi2Gzal

— hardmaru (@hardmaru) September 17, 2018

Implementation of Everybody Dance Now by pytorch https://t.co/8etHXuQyVZ #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch

— PyTorch Best Practices (@PyTorchPractice) September 15, 2018

Pytorch implementation of the deep dream computer vision algorithm https://t.co/pgvPiHGGuQ #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch

— PyTorch Best Practices (@PyTorchPractice) September 1, 2018

PolygonRNN++: an official @PyTorch reimplementation for Efficient Interactive Annotation of Segmentation Datasets by @davidjesusacu, Huan Ling, @amlankar95 and @FidlerSanja
README: https://t.co/Gruf1bfbna
Code: https://t.co/fUvTN7TS6j pic.twitter.com/0BzDaTwKPk

— PyTorch (@PyTorch) August 15, 2018

If you use @PyTorch, I've written up a bunch of notes on how I think about it, tips, and common gotchas: https://t.co/E3AJFBQuEI

— Kaixhin (@KaiLashArul) July 27, 2018

[v0.4.1] Spectral Norm, Adaptive Softmax, faster CPU ops, anomaly detection (NaNs, etc.), Lots of bug fixes, Python 3.7 and CUDA 9.2 support and more. Full release notes at https://t.co/ylwAO7AGGp
As always, update via commands at https://t.co/DeaBDT98QI or via PyPI

— PyTorch (@PyTorch) July 26, 2018

New version 0.3.0 of skorch is out https://t.co/hVoFBaztrr. You can now run parallel grid searches across multiple GPUs using dask 👏

— Ethan Rosenthal (@eprosenthal) July 26, 2018