Stars
Symbolica is a high-performance computer algebra library for Python and Rust. Manipulate large expressions, match patterns, and generate optimized numerical code — at unprecedented speed.
The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch
🐍 Geometric Computer Vision Library for Spatial AI
Torchreid: Deep learning person re-identification in PyTorch.
A differentiable PDE solving framework for machine learning
An GPU/CUDA implementation of the Hungarian algorithm
A differentiable LCP physics engine in PyTorch.
This library adds a new Font() object to the JavaScript toolbox, similar to new Image() for images
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
python implementation of "high-speed tracking with kernelized correlation filters"
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
Walk through an infinite, procedurally generated city
A PyTorch implementation for Unsupervised Data Augmentation
Unofficial PyTorch Implementation of Unsupervised Data Augmentation.
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
Invariant Information Clustering for Unsupervised Image Classification and Segmentation
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
Converted from [tf+keras version MASK-RCNN](https://github.com/matterport/Mask_RCNN)
PyTorch implementation of [1412.6553] and [1511.06530] tensor decomposition methods for convolutional layers.
A Lasagne layer (and supporting Theano Ops) for the CRF-as-RNN layer.
Simple benchmark of deep learning frameworks on VGG-16
Lasagne recipes: examples, IPython notebooks, ...