First fastai v2 starter pack! :O
— Jeremy Howard (@jeremyphoward) September 30, 2019
(Note that v2 is very very pre-release - @radekosmulski is an early adopter!) https://t.co/52X2mULm7y
First fastai v2 starter pack! :O
— Jeremy Howard (@jeremyphoward) September 30, 2019
(Note that v2 is very very pre-release - @radekosmulski is an early adopter!) https://t.co/52X2mULm7y
🤗Transformers 2.0💥
— Thomas Wolf (@Thom_Wolf) September 26, 2019
State-of-the-art NLP in TensorFlow 2.0/PyTorch
8 architectures
33 trained models
102 lang.
Seamlessly pick the right framework for training, eval, deploy
Train on TPU ⏩ finetune/test in PyTorch ⏩ serve w. TFX
🍒Keras magic: train SOTA model in 10 lines👇 pic.twitter.com/K7BNdxDBQh
I came across this really awesome explanation and comparison of a variety of methods to estimate predictive intervals from neural networks (in PyTorch). A great starting point if you’re thinking about how to add uncertainty to your model. https://t.co/cpdUfP3dXh pic.twitter.com/fzs8obZST4
— Sean J. Taylor (@seanjtaylor) September 19, 2019
Taking face censoring one more step: replace them with randomly generated face at the correct pose.
— Reza Zadeh (@Reza_Zadeh) September 11, 2019
Paper: https://t.co/T2edC4VGXB
Code: https://t.co/F7iUh2lJVt pic.twitter.com/XqxKo041bG
time to try out BoTorch. looks great https://t.co/vXbYW786KD
— Kyunghyun Cho (@kchonyc) September 9, 2019
Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples" https://t.co/i8zfOFPiQd #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) September 5, 2019
The excellent interactive book "Dive into Deep Learning" has been ported to PyTorch by students at IIT Roorkeehttps://t.co/6gt457L4oq
— PyTorch (@PyTorch) August 27, 2019
The book was authored by @astonzhangAZ, @zacharylipton @mli65 et. al. https://t.co/NQRcbbeO0G
audio - Data manipulation and transformation for audio signal processing, powered by PyTorch https://t.co/uuomjXSjYL
— Python Trending (@pythontrending) August 12, 2019
Talks from our recent hackathon are available here, covering the PyTorch 1.2 release and revamped domain libraries - torchaudio 0.3, torchtext 0.4, and torchvision 0.4: https://t.co/PcaYkHBkru
— PyTorch (@PyTorch) August 12, 2019
Goodies:
— Yann LeCun (@ylecun) August 9, 2019
- PyTorch v1.2: TorchScript improvements, expanded transformer support, expanded ONNX support, TensorBoard support
- TorchAudio v0.3: new functions, API cleanup, Kaldi compatibility
- TorchVision v0.4: support for video
- TorchText v0.4:... https://t.co/oF10AiXsUB
A question I get from time to time is how to convert a pretrained TensorFlow model in PyTorch easily and reliably.
— Thomas Wolf (@Thom_Wolf) August 9, 2019
We're starting to be quite familiar with the process so I've written a short blog post summarizing our workflow and some lessons learned 👇https://t.co/d8ZMs30nGq
[torchaudio v0.3]: Standardization, JIT/CUDA Support, Kaldi Compliance Interface (matching Kaldi preprocessing exactly), inverse STFT:https://t.co/AtQ0FUoCa7
— PyTorch (@PyTorch) August 8, 2019