PyTorch Lightning 1.0.0 is now available. This is the final stable API to train and deploy models at scale, without the boilerplate. Read more about this release below: https://t.co/9zozqQWOCL
— PyTorch (@PyTorch) October 21, 2020
PyTorch Lightning 1.0.0 is now available. This is the final stable API to train and deploy models at scale, without the boilerplate. Read more about this release below: https://t.co/9zozqQWOCL
— PyTorch (@PyTorch) October 21, 2020
The robotics team @arrival, a zero-emission solutions company, demonstrates how to apply deep reinforcement learning (DRL) to solve your own robotic challenge in this tutorial. Learn how to solve the peg-in-hole insertion task using Catalyst/CatalystRL: https://t.co/SLNZaiHoDp
— PyTorch (@PyTorch) October 13, 2020
An open-source PyTorch library for Graph Transformer Networks.
— Yann LeCun (@ylecun) October 8, 2020
Allows you to build DL systems that perform operations on weighted graphs and bakcpropagate gradients through these operations.
(this is different from graph neural nets).
From FAIR.https://t.co/e6iMzPMLhB
Introducing TensorSensor: a lib that clarifies exceptions by augmenting messages + visualizing Python code to indicate shape of tensor variables; works with Tensorflow, PyTorch, Numpy, and higher-level libraries like Keras and fastai. Article: https://t.co/lqZgWOu4FC pic.twitter.com/1sVLaOcOfQ
— Terence Parr (@the_antlr_guy) October 6, 2020
PyTorch/XLA, a package that lets PyTorch connect to @GCPcloud TPUs and use TPU cores as devices, is now generally available. Highlights:
— PyTorch (@PyTorch) September 29, 2020
- Support for Intra-Layer Model Parallelism
- Additional XLA ops
- Integrations with Colab and Kaggle notebookshttps://t.co/VwgPHlqe5M
Introducing #Imaginaire
— Ming-Yu Liu (@liu_mingyu) September 28, 2020
a #PyTorch library with optimized implementations of several #GAN image and video synthesis methods developed at #NVIDIA
code https://t.co/fWMHEwhS3q
video https://t.co/BUkEE7RB3D
By @liu_mingyu @tcwang0509 @arunmallya @xunhuang1995 pic.twitter.com/ludgIdT4U0
Poutyne is a Keras-like framework for PyTorch and handles much of the boilerplating code needed to train neural networks. https://t.co/9xFtqBzGvQ #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) September 24, 2020
Silero AI adds fast and accurate speech recognition models for English, German and Spanish to the PyTorch Hub.
— PyTorch (@PyTorch) September 23, 2020
Try them out today!https://t.co/gkRPTU15mO
Have you ever wondered why the recommended approach to store a model in @PyTorch is to save the state dict rather than the model itself? Here is an illustration of the rationale behind one of the more undervalued and underobserved PyTorch best practices:https://t.co/pbA28x6Vc9 pic.twitter.com/DCLNgWOAYe
— Thomas Viehmann (@ThomasViehmann) September 11, 2020
The full hands-on tutorials, "Building Recommender Systems with PyTorch", are now available. We show how to build deep learning recommendation system and resolve the associated interpretability, integrity, and privacy challenges. See: https://t.co/vaqkdhpvyr
— PyTorch (@PyTorch) September 10, 2020
This might not be obvious yet, but this is one of the biggest things we’ve released so far. https://t.co/5mBANyY7us
— Julien Chaumond (@julien_c) September 10, 2020
Bolts is a new Deep Learning research and production toolbox from PyTorch Lightning. Iterate faster with pre-trained models, components, callbacks, and data sets, all modular, tested, and optimized for GPUs/TPUs.
— PyTorch (@PyTorch) September 10, 2020
Simply subclass, override, and train. https://t.co/qYjCMdyv4i