Github PK Tool:Github PK Tool
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)
A PyTorch port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)
Dual Path Networks (DPN) supporting pretrained weights converted from original MXNet implementation
Quick docker based reader for udacity rosbag self-driving dataset. Dumps to png/jpg + csv or Tensorflow examples.
EfficientNet, MobileNetV3, MobileNetV2, MixNet, etc in JAX w/ Flax Linen and Objax
Well trained MXNet Gluon Model Zoo ResNet/ResNeXt/SE-ResNeXt ported to PyTorch
Some PyTorch code for the Kaggle Speech Recognition Challenge
PyTorch based Reinforcement Learning for OpenSim Prosthetics and Learning to Run environments
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
PyTorch & Rainbow for Obstacle Tower Challenge
An open source implementation of CLIP.
Google Brain AutoML
Datasets, Transforms and Models specific to Computer Vision
Download kinetics and prepare '.json' annotations for each subset
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
PPO/A2C in PyTorch for the Obstacle Tower Challenge
Optax is a gradient processing and optimization library for JAX.
A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
Example code and applications for machine learning on Graphcore IPUs
Open MMLab Detection Toolbox and Benchmark
Paired Open-Ended Trailblazer (POET) and Enhanced POET