Ross Wightman

efficientdet-pytorch. A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

gen-efficientnet-pytorch. Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

posenet-python. A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

posenet-pytorch. A PyTorch port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

pytorch-dpn-pretrained. Dual Path Networks (DPN) supporting pretrained weights converted from original MXNet implementation

udacity-driving-reader. Quick docker based reader for udacity rosbag self-driving dataset. Dumps to png/jpg + csv or Tensorflow examples.

efficientnet-jax. EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax

pytorch-nips2017-attack-example. A PyTorch baseline attack example for the NIPS 2017 adversarial competition

timm. PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

genalog. Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

tensorflow-litterbox. Tensorflow experimentation sandbox. VGG, ResNet, Inception V3, Inception V4, Inception-Resnet-V2 models.

pytorch-pommerman-rl. PyTorch RL for Pommerman

pytorch-planet-amazon. PyTorch models and training code for 'Planet: Understanding the Amazon from Space' Kaggle

imagenet-12k. ImageNet-12k subset of ImageNet-21k (fall11)

pytorch-pretrained-gluonresnet. Well trained MXNet Gluon Model Zoo ResNet/ResNeXt/SE-ResNeXt ported to PyTorch

pytorch-opensim-rl. PyTorch based Reinforcement Learning for OpenSim Prosthetics and Learning to Run environments

pytorch-nips2017-adversarial. NIPS 2017 Adversarial Competition in PyTorch

py-lmdb. Universal Python binding for the LMDB 'Lightning' Database

pytorch-commands. Some PyTorch code for the Kaggle Speech Recognition Challenge

pytorch-countception-sealion. Pytorch implementation of Count-ception and custom CNN counting models for Kaggle Sea Lion Count challenge

pytorch-nips2017-defense-example. A PyTorch baseline defense example for the NIPS 2017 adversarial competition

tensorflow. Computation using data flow graphs for scalable machine learning

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

open_clip. An open source implementation of CLIP.

tensorflow-annex. A module for converting datasets + annotations to sharded Tensorflow TFRecords files

tensorflow-speech_commands. Speech commands training/models from TF repo adapted for speech commands Kaggle

tensorflow-models. Models built with TensorFlow

obstacle-tower-pytorch-rainbow. PyTorch & Rainbow for Obstacle Tower Challenge

huggingface_hub. All the open source things related to the Hugging Face Hub.

tensorflow-models-slim. Filtered research/slim folder from tensorflow models repository. With experiments and additions.

mmdetection. Open MMLab Detection Toolbox and Benchmark

vision. Datasets, Transforms and Models specific to Computer Vision

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

pytorch. C++

automl. Google Brain AutoML

obstacle-tower-pytorch-a2c-ppo. PPO/A2C in PyTorch for the Obstacle Tower Challenge

pytorch-docker. Dockerfile definitions with matching Docker Hub images for PyTorch

kinetics-download-prep. Download kinetics and prepare '.json' annotations for each subset

playground. PlayGround: AI Research into Multi-Agent Learning.

M4-methods. Includes the source code of the methods which participated in the M4 Competition

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

objax. Python

DensePose. A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

optax. Optax is a gradient processing and optimization library for JAX.

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

harmonicConvolutions. Deep Translation and Rotation Equivariance

capnproto. Cap'n Proto serialization/RPC system

graphcore-examples. Example code and applications for machine learning on Graphcore IPUs

detectron2. Detectron2 is FAIR's next-generation platform for object detection and segmentation.

self-driving-car. Information about the Udacity open source self-driving car project