Here is an unofficial implementation of "Learning Confidence for Out-of-Distribution Detection in Neural Networks"

TensorRT implementation of "RepVGG: Making VGG-style ConvNets Great Again"

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Our ICCV Submission materials

Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers a…

QKeras: a quantization deep learning library for Tensorflow Keras

Convert Bayer (RGGB) pixel pattern into a 3 channel RGB color representation.

A model compression and acceleration toolbox based on pytorch.

Simple Python and Julia implementations of the 1€ Filter. The codes can be used as a pseudocode for implementing the algorithm in other languages.

Real time one-stage multi-class & multi-object tracking based on anchor-free detection and ReID

source code for ICLR'22 paper "VOS: Learning What You Don’t Know by Virtual Outlier Synthesis"

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉

pytorch -> onnx -> caffe, pytorch to caffe, or other deep learning framework to onnx and onnx to caffe.

[TPAMI 2022 & CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

Code for "Image-to-image Translation via Hierarchical Style Disentanglement" (CVPR 2021 Oral).

[ECCV 2020] SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation

Code repository for the paper: "Coherent Reconstruction of Multiple Humans from a Single Image" in CVPR'20

Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

Scripts to manage COCO datasets

Awesome work on hand pose estimation/tracking

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

PyTorch C++ inference with LibTorch

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

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

A collection of AWESOME things about domian adaptation