Aditya Oke wrote a beginner tutorial on how to create a simple image search engine using PyTorch. The blog post walks through using auto-encoder, managing the dataset, training and saving the feature representations, and more with actual code samples. https://t.co/fUUhCcPDhw
— PyTorch (@PyTorch) September 2, 2020
Catalyst is a PyTorch library that helps you write DL pipelines with a few lines of code. It now offers metric learning, enabling feature extractor by mapping objects from the same class into the nearest points and distancing points for different classes. https://t.co/UDQLRJxrBk
— PyTorch (@PyTorch) September 2, 2020
good quick tutorial on optimizing your PyTorch code ⏲️: https://t.co/7CIDWfrI0J
— Andrej Karpathy (@karpathy) August 30, 2020
quick summary: pic.twitter.com/6J1SJcWJsl
torchcsprng is a PyTorch C++/CUDA extension that provides cryptographically secure pseudorandom number generators for PyTorch based on Salmon et. al's "Parallel Random Numbers". Learn more:https://t.co/OQMrk5Y77C
— PyTorch (@PyTorch) August 24, 2020
Stochastic Weight Averaging (SWA) is a simple procedure that improves generalization in deep learning over Stochastic Gradient Descent (SGD). PyTorch 1.6 now includes SWA natively. Learn more from @Pavel_Izmailov, @andrewgwils and Vincent: https://t.co/1u5yRwfWXT
— PyTorch (@PyTorch) August 18, 2020
A PyTorch implementation of MobileNetV3 for real-time semantic segmentation, with state-of-the-art performance https://t.co/MYE7mwOWy4 #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) August 12, 2020
WebDataset is a PyTorch dataset that scales. It is backed by the POSIX tar standard and is simple yet efficient. Learn how the library can help you work with large datasets and distributed training in PyTorch. https://t.co/6gS473kumt
— PyTorch (@PyTorch) August 11, 2020
"EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy": https://t.co/7981r7nN5H Looks like a neat tool when collaborating with people who prefer a different Deep Learning lib, and you want to find a common denominator.
— Sebastian Raschka (@rasbt) August 11, 2020
AllenNLP is now integrated with Optuna, a hyperparameter optimization library, enabling users to reuse an AllenNLP Jsonnet configuration file to optimize hyperparameters. Read this tutorial to learn more: https://t.co/53y66pmpph
— PyTorch (@PyTorch) August 5, 2020
Writing better code with PyTorch and einops https://t.co/GTIWdttOhu 👌
— Andrej Karpathy (@karpathy) August 5, 2020
PyTorch 1.6 is out: https://t.co/wDZ9FZqQls ! Excited to take the profiler for a spin pic.twitter.com/SBhghiz0Ug
— Sebastian Raschka (@rasbt) July 28, 2020
v1.6: native mixed-precision support from NVIDIA (~2x perf improvement), distributed perf improvements, new profiling tool for memory consumption, Microsoft commits to developing and maintaining Windows PyTorch.
— PyTorch (@PyTorch) July 28, 2020
Release Notes: https://t.co/7LMXQYlaAd
Blog:https://t.co/0cwKG82iOB
