Alternatives and similar repositories for DeepFusion

Users that are interested in DeepFusion are comparing it to the libraries listed below

• yhwang-hub / dl_model_infer
  🚀🚀🚀This is an AI high-performance reasoning C++ library, Currently supports the deployment of yolov5, yolov7, yolov7-pose, yolov8, yol…
  ☆134Updated last year
• Susan19900316 / yolov5_tensorrt_int8
  yolov5 tensorrt int8量化方法汇总
  ☆83Updated last year
• CYYAI / AiInfer
  ☆114Updated last year
• leon0514 / trt-sahi-yolo
  tensorrt sahi yolo 目标检测
  ☆77Updated 2 weeks ago
• heyongxin233 / YOLO-Pruning-RKNN
  Easy Training Official YOLOv11、YOLOv10、YOLOv8、YOLOv7、YOLOv6、YOLOv5 and Prune all_model using Torch-Pruning!
  ☆97Updated last month
• huangzongmou / yolov8-pytorch_quantization
  使用pytorch_quantization对yolov8进行量化
  ☆118Updated last year
• shouxieai / algorithm-cpp
  algorithm-cpp projects
  ☆79Updated 3 years ago
• cqu20160901 / yolov11_deploymethods
  yolov11（yolov8）尝试了7种不同的部署方法，并对每种方法的优势进行了简单总结。不同的平台、不同的时耗或CPU占用需求，总有一种方法是适用的。针对想入门部署的也是一个很好的参考学习资料。
  ☆37Updated 8 months ago
• thb1314 / mmyolo_tensorrt
  ☆150Updated last year
• yzy12-max / yolov5_deploy
  ☆52Updated 2 years ago
• huangzongmou / yolov8_Distillation
  ☆99Updated last year
• Zhou-wy / TRT-YOLOv8-Seg
  使用TensorRT加速YOLOv8-Seg，完整的后端框架，包括Http服务器，Mysql数据库，ffmpeg视频推流等。
  ☆85Updated last year
• sesmfs / onnx_matcher
  Using pattern matcher in onnx model to match and replace subgraphs.
  ☆81Updated last year
• yhwang-hub / dl_model_deploy
  ☆79Updated 2 years ago
• l-sf / Linfer
  基于TensorRT的C++高性能推理库，Yolov10, YoloPv2，Yolov5/7/X/8，RT-DETR，单目标跟踪OSTrack、LightTrack。
  ☆209Updated last year
• emptysoal / cuda-image-preprocess
  Speed up image preprocess with cuda when handle image or tensorrt inference
  ☆77Updated 2 weeks ago
• cqu20160901 / yolov8n_onnx_tensorRT_rknn_horizon_dfl
  yolov8n 目标检测部署版本，便于移植不同平台（onnx、tensorRT、rknn、Horizon），全网部署最简单、速度最快的部署方式。
  ☆46Updated last year
• Rex-LK / tensorrt_learning
  ☆131Updated last year
• CVHub520 / rtdetr-onnxruntime-deploy
  This project showcases the deployment of the RT-DETR model using ONNXRUNTIME in C++ and Python.
  ☆56Updated 2 years ago
• twlelev / OpenVINO_CPP_YOLOX-YOLOV5-YOLOV8-YOLOV9
  C++ inference of YOLOX/YOLOV5/YOLOV8/YOLOV9 for OpenVINO,Support float32、float16 and int8.
  ☆66Updated last year
• cqu20160901 / yolov11_tensorRT_postprocess_cuda
  yolov11 的tensorRT C++ 部署，后处理使用cuda实现比较耗时的操作。
  ☆42Updated 2 weeks ago
• shouxieai / hard_decode_trt
  Yolov5 inference on NVDec hardware decoder
  ☆88Updated 3 years ago
• mytk2012 / YOLOV8_INT8_TRT
  ☆15Updated last year
• fish-kong / Yolov5-obb-Tensorrt-Infer
  11111
  ☆28Updated 2 years ago
• Melody-Zhou / tensorRT_Pro-YOLOv8
  This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.
  ☆376Updated 3 months ago
• raymond1123 / Flash-Attention
  ☆25Updated 10 months ago
• emptysoal / TensorRT-YOLOv8
  Based on tensorrt v8.0+, deploy detect, pose, segment, tracking of YOLOv8 with C++ and python api.
  ☆123Updated last month
• LSH9832 / yolov8_trt
  A quick TensorRT deoloyment solution for YOLOv8.
  ☆39Updated last year
• thb1314 / tensorrt-onnx-fasterrcnn-fpn-roialign
  ☆52Updated 2 years ago
• huangzongmou / Pycuda-warpaffine-trt-post
  使用pycuda对图片进行预处理
  ☆27Updated 2 years ago