The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

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

Porting vision models to Keras 3 for easily accessibility. Contains MobileViT v1, MobileViT v2

Learn OpenCV : C++ and Python Examples

PyTorch Implementation of the state-of-the-art model for object detection EfficientDet [pre-trained weights provided]

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

Code and models for mobile-former

Lite Vision Transformer (CVPR 2022)

Official implementation for paper "LightViT: Towards Light-Weight Convolution-Free Vision Transformers"

[ECCV 2022] EdgeViT: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

CVNets: A library for training computer vision networks

TensorFlow implementation of the Xception Model by François Chollet

[ICCV2019] ThunderNet: Towards Real-time Generic Object Detection on Mobile Devices

A tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

Pelee: A Real-Time Object Detection System on Mobile Devices

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Reference models and tools for Cloud TPUs.

EfficientDet (Scalable and Efficient Object Detection) implementation in Keras and Tensorflow

Google Brain AutoML

Models and examples built with TensorFlow