⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

它是一个工作流。可快速构建指定架构/平台的docker镜像

Pytorch Feature Map Extractor

[ICLR 2023] OTOv2: Automatic, Generic, User-Friendly; [NeurIPS 2021] Only Train Once: A One-Shot Neural Network Training And Pruning Framework

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

Pytorch Lightning Implementation of SC-Depth (V1, V2...) for Unsupervised Monocular Depth Estimation.

Custom Implementation of Non-Deep Networks

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）

PyTorch code for training EfficientPS for Panoptic Segmentation https://rl.uni-freiburg.de/research/panoptic

This is an unofficial implementation of the paper “PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization”.

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

OpenMMLab Image Classification Toolbox and Benchmark

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.

GUI for marking bounded boxes of objects in images for training neural network Yolo v3 and v2

Windows version of Yolo Convolutional Neural Networks

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

[NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2…

NVIDIA DeepStream SDK 5 configuration for YoloV4 and YoloV3 model

PointTrack (ECCV2020 ORAL): Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

The Triton Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.

Implementations of Fourier Transform, Laplacian Pyramids, Edge Detection

OpenMMLab Detection Toolbox and Benchmark

MobileNet-SSD, MobileNetV2-SSD/SSDLite on VOC, BDD100K Datasets.

Tensor Low-rank Reconstruction for Semantic Segmentation