Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Deep universal probabilistic programming with Python and PyTorch
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
A system for quickly generating training data with weak supervision
⛹️ Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
A highly efficient implementation of Gaussian Processes in PyTorch
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.
KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows
Geometric loss functions between point clouds, images and volumes
Type hints support for the Sphinx autodoc extension
Code for "Latent ODEs for Irregularly-Sampled Time Series" paper
Probabilistic Numerics in Python.
Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".
Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"
Accelerated pose estimation and tracking using semi-supervised convolutional networks.
A plug-in replacement for DataLoader to load Imagenet disk-sequentially in PyTorch.
A PyTorch implementation of a Factorization Machine module in cython.
A memory efficient implementation of densenet.
Implementation of the Gaussian Process Autoregressive Regression Model
[ICML'18] Scalable Gaussian Processes with Grid-Structured Eigenfunctions