dog-qiuqiu / Yolo-Fastest
Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
☆2,006Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for Yolo-Fastest
- Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smar…☆808Updated 9 months ago
- TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is usef…☆1,192Updated last year
- NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone…☆5,753Updated 3 months ago
- 🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。☆1,476Updated 2 years ago
- yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏☆1,501Updated 4 years ago
- A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by …☆774Updated last year
- PyTorch implementation of YOLOv4☆1,880Updated this week
- Scaled-YOLOv4: Scaling Cross Stage Partial Network☆2,018Updated this week
- YOLOv3、YOLOv4、YOLOv5、YOLOv5-Lite、YOLOv6-v1、YOLOv6-v2、YOLOv7、YOLOX、YOLOX-Lite、PP-YOLOE、PP-PicoDet-Plus、YOLO-Fastest v2、FastestDet、YOLOv5-S…☆748Updated 2 years ago
- yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.☆720Updated last week
- Implementation of popular deep learning networks with TensorRT network definition API☆6,984Updated 2 weeks ago
- TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet☆1,745Updated 3 months ago
- Pytorch YOLO v5 训练自己的数据集超详细教程！！！ (提供PDF训练教程下载）☆914Updated 2 years ago
- 🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~☆2,263Updated 4 months ago
- support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++☆826Updated last year
- mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！☆822Updated 2 years ago
- PyTorch ,ONNX and TensorRT implementation of YOLOv4☆4,479Updated 4 months ago
- YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)☆2,097Updated 3 months ago
- ☆706Updated last year
- This page is for the SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications☆1,143Updated 5 years ago
- A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle de…☆1,315Updated 3 years ago
- implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)☆1,986Updated this week
- MOT using deepsort and yolov3 with pytorch☆2,817Updated 3 months ago
- 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥☆3,123Updated 11 months ago
- The YOLOv5 object detection android example☆642Updated last year
- Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms☆718Updated last year
- 用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序☆513Updated 2 years ago
- ☆818Updated 10 months ago
- TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据☆523Updated 3 years ago
- yolov5 prune，Support V2, V3, V4 and V6 versions of yolov5☆560Updated 2 years ago