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
⚡️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
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
🔔 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
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 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
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 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 ⬇️
#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
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
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 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
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.