Great to see there's now a general interpolation library for @PyTorch :)https://t.co/NdiPReT6p5 pic.twitter.com/qxnWDcKN7w
— Jeremy Howard (@jeremyphoward) July 16, 2020
Great to see there's now a general interpolation library for @PyTorch :)https://t.co/NdiPReT6p5 pic.twitter.com/qxnWDcKN7w
— Jeremy Howard (@jeremyphoward) July 16, 2020
Disney uses PyTorch for animated character recognition and to speed up its video processing pipeline. @DTCITechnology engineers also contributed new features to the Torchvision domain library. https://t.co/2DxwcTRtoF
— PyTorch (@PyTorch) July 16, 2020
Jirka, Lead contributor for Lightning, and Zach, ML Engineer at Google, discuss how PyTorch Lightning became the first ML framework to run continuous integration on TPUs in this blog post. https://t.co/zk78fnTF2s
— PyTorch (@PyTorch) July 10, 2020
Allegro Trains, a full system ML/DL experiment manager, versioning, and ML-Ops solution, joined the PyTorch Ecosystem Project. In this blog post, @allegroAI walks through an image classification example demonstrating how to manage numerous experiments. https://t.co/gYBHn4LAa3
— PyTorch (@PyTorch) July 9, 2020
90% of the time your image classifier is not working as expected it's because of (1) image resizing issues (2) batch-norm :) https://t.co/DYX8EEl68Z
— Dumitru Erhan (@doomie) July 8, 2020
Short educational talks on various PyTorch topics such as the latest updates, Pruning, Torchaudio, PyTorch3D, PyTorch Mobile Runtime on iOS/Android and more are now available on the PyTorch YouTube Channel. https://t.co/VjTtdbvOnJ
— PyTorch (@PyTorch) July 6, 2020
The full version of the Deep Learning with PyTorch book from Luca Antiga, Eli Stevens, and Thomas Viehmann is now available! New chapters include in-depth real-world examples and production deployment. Grab a free digital copy on: https://t.co/RNUUKbAZTs
— PyTorch (@PyTorch) July 6, 2020
Captum is a model interpretability library for PyTorch which offers a number of attribution algorithms that help understand the importance of input feature, and hidden neurons and layers. Check out this deep dive to learn more:https://t.co/pE4NG6s8lv
— PyTorch (@PyTorch) July 2, 2020
PyTorch Lightning 0.8.4 now provides a Metrics package, for tens of common out of the box metrics (eg. ROC, PR, ConfusionMatrix, F1, etc.), along with a scikit-learn interface as well. Learn more: https://t.co/h9z418JdtJ
— PyTorch (@PyTorch) July 1, 2020
Automate the tuning of hyperparameters with PyTorch Ignite using Bayesian Optimisation in Optuna. Learn more: https://t.co/VxOgKGxXbh
— PyTorch (@PyTorch) June 25, 2020
Check out this tutorial from the Catalyst team on how to distillate BERT models. Distilling BERT models can minimize accuracy loss, reduce model sizes, and speed up inferences.https://t.co/uBvba5NObZ
— PyTorch (@PyTorch) June 24, 2020
PyTorch Lightning 0.8.1 is now available. This new release includes a PyTorch multi-GPU metrics package, the ability to overfit on a small subset of data, faster multi-GPU training, and more. Read: https://t.co/jn1iaxMEcN
— PyTorch (@PyTorch) June 21, 2020