Learn PyTorch

Tutorial and examples for PyTorch

[Learn PyTorch @learnpytorch]

PyTorch 2.0 is now available, with new features like torch.compile(), faster and more pythonic than ever #PyTorch

[Learn PyTorch @learnpytorch]

Lightning 2.0 is out⚡️with an exciting Fabric for scaling up any PyTorch model

[Lightning AI ⚡️ @LightningAI]

With the help of our community, we are excited to announce PyTorch Lightning 2.0🎉🎉

Install now 👉https://t.co/Y4rxJpRkDG

Highlights Include:
⚡️ Commitment to backward compatibility in the 2.0 series
⚡️Simplified abstraction layers, removed legacy functionality, integrations out of the main repo. This improves the project's readability and debugging experience.
⚡️Introducing Fabric! Scale any PyTorch model with just a few lines of code.

#PyTorch #PyTorchLightning

[Learn PyTorch @learnpytorch]

Keypoint detection using PyTorch Lightning ⚡️@LightningAI ⚡️ and wandb (https://t.co/kvTFS5NTzF)

https://t.co/kmalF0yILH
#PyTorch

[Learn PyTorch @learnpytorch]

#PyTorch quiz: calculating the cross-entropy loss of a 3-class problem assuming fully random prediction

[Lightning AI ⚡️ @LightningAI]

⚡️POP QUIZ TIME!⚡️

Suppose you have 2 training examples in a 3-class classification setting. What is the cross-entropy loss for a perfectly random prediction?

Need a refresher? Start unit 4 of @rasbt's Deep Learning course! 👉👉 https://t.co/o3JwoBemEW

[Learn PyTorch @learnpytorch]

Speed-up in inference time for Stable Diffusion obtained by @LightningAI #deeplearning

[Lightning AI ⚡️ @LightningAI]

We made it three times faster to serve Stable Diffusion 🏎️💨💨💨

Here’s how we did it 🧵...

(1/6)

[Learn PyTorch @learnpytorch]

A nice tutorial video on using Optuna and PyTorch for auto-tuning hyperparameters: https://t.co/uUrnnpQtaS
#DataScience #DeepLearning #MachineLearning

[Learn PyTorch @learnpytorch]

Why #PyTorch?
1. PyTorch feels more pythonic
2. Available models in PyTorch
3. PyTorch is better for students and research
4. PyTorch's ecosystem has grown faster

[Yann LeCun @ylecun]

Why? PyTorch. That's why.

https://t.co/AF4Q2KmFQu

[PyTorch @PyTorch]

🔔 Our Next Live Q&A: How and why you should contribute to tutorials and code to PyTorch w/ @ZainRzv, @shshnkp, @laignas and Carl Parker.

🗓️ December 15 @ 2pm PT

Watch this talk in advance to learn more: https://t.co/3R691NwcFt

[Learn PyTorch @learnpytorch]

Quick intro to PyTorch 2.0, and its new features such as torch.compile, followed by finetuning a BERT model with PyTorch 2.0 and HuggingFace 🤗Transformers https://t.co/08opL2N0pT
#PyTorch

[Learn PyTorch @learnpytorch]

Language Translation #tutorials with #PyTorch

[PyTorch @PyTorch]

Learn about language translation w/ nn.transformer & torchtext today for #TutorialTuesdays. We’ll show you how to use torchtext’s inbuilt datasets, tokenize a raw text sentence, build vocabulary, and convert tokens into tensor.

Follow the tutorial ➡️ https://t.co/zfOcrIvLkm

[PathAI @Path_AI]

At the @PyTorch Developer Conference 2022, join our @Path_AI team during their poster presentation on December 2nd to learn more about our work on interpretable models for #pathology. Read the full paper here: https://t.co/68BLFVhnC2

[Learn PyTorch @learnpytorch]

#TutorialTuesdays Training a nn.Transformer model in #pytorch

[PyTorch @PyTorch]

Learn how to train a nn.Transformermodel on a language modeling task this week on #TutorialTuesdays:

1️⃣ Define the model
2️⃣ Load & batch data
3️⃣ Initiate an instance
4️⃣ Run the model
5️⃣ Evaluate the best model on the test dataset

Read more about nn.Transformer ⬇️

[PyTorch @PyTorch]

#PyTorchConference is 18 days away!

Join PyTorch co-creator @soumithchintala, PyTorch Foundation Exec Dir @ibrahimatlinux and other ML experts live in-person on Dec 2 as they deliver technical talks & share posters.

Seating is limited, apply now! https://t.co/JSXnyVGo8N

[PyTorch @PyTorch]

TorchVision v0.9 has been released and is packed with many #ML models and features, speed improvements and bug fixes. Check out the overview of the new models here: https://t.co/qdRp0gjRCq

[Pete Skomoroch @peteskomoroch]

Using PyTorch + NumPy? You're making a mistake.
A bug that plagues thousands of open-source ML projects: https://t.co/N84FUBQpyH

[PyTorch @PyTorch]

Introducing torch.profiler! New PyTorch Profiler collects both GPU and framework related info, correlates them, performs automatic detection of bottlenecks in the model, generates recommendations on how to resolve these bottlenecks, and visualize.

Read 👉https://t.co/Ottly5CtF4

[PyTorch @PyTorch]

PyTorch 1.8 is here!

Highlights include updates for compiler, code optimization, frontend APIs for scientific computing, large scale training for pipeline and model parallelism, and Mobile tutorials.

Blog👇https://t.co/AssGYBfWKi

[KDnuggets @kdnuggets]

The Most Complete Guide to #PyTorch for Data Scientists - KDnuggets https://t.co/BxKeqjTLzg

[Alfredo Canziani @alfcnz]

Week ⑪ videos 🎥 are up! 🎉

Lecture: https://t.co/2HzhcSTlFC
Practicum: https://t.co/vxnGk5baZE
Transcript: https://t.co/yzPxvEssYR

Learn about:
• all @PyTorch activation and loss functions;
• how to make predictions and training policies under uncertainty.

[Learn PyTorch @learnpytorch]

All presented papers at ICLR (virtual-2020): https://t.co/DqmEKpEfvO