All Projects → cmdbug → TNN_Demo

cmdbug / TNN_Demo

Licence: GPL-3.0 license
🍉 移动端TNN部署学习笔记,支持Android与iOS。

Programming Languages

C++
36643 projects - #6 most used programming language
c
50402 projects - #5 most used programming language

Projects that are alternatives of or similar to TNN Demo

realtime-object-detection
Detects objects in images/streaming video
Stars: ✭ 16 (-68.63%)
Mutual labels:  yolo, yolov5
Yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Stars: ✭ 19,914 (+38947.06%)
Mutual labels:  yolo, yolov5
lite.ai.toolkit
🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, MODNet, YOLOR, NanoDet, YOLOX, SCRFD, YOLOX . MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.
Stars: ✭ 1,354 (+2554.9%)
Mutual labels:  tnn, nanodet
Vehicle-Detection
Vehicle Detection Using Deep Learning and YOLO Algorithm
Stars: ✭ 96 (+88.24%)
Mutual labels:  yolo, yolov5
ros-yolo-sort
YOLO v3, v4, v5, v6, v7 + SORT tracking + ROS platform. Supporting: YOLO with Darknet, OpenCV(DNN), OpenVINO, TensorRT(tkDNN). SORT supports python(original) and C++. (Not Deep SORT)
Stars: ✭ 162 (+217.65%)
Mutual labels:  yolo, yolov5
make-your-yolov5 dataset
💥Make your yolov5 dataset by using labelimg.I hope my work can help you make your yolov5 datasets more quickly.
Stars: ✭ 60 (+17.65%)
Mutual labels:  yolo, yolov5
Yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
Stars: ✭ 8,159 (+15898.04%)
Mutual labels:  yolo, yolov5
food-detection-yolov5
🍔🍟🍗 Food analysis baseline with Theseus. Integrate object detection, image classification and multi-class semantic segmentation. 🍞🍖🍕
Stars: ✭ 68 (+33.33%)
Mutual labels:  yolo, yolov5
YOLOX deepsort tracker
using yolox+deepsort for object-tracking
Stars: ✭ 228 (+347.06%)
Mutual labels:  yolo, yolov5
JSON2YOLO
Convert JSON annotations into YOLO format.
Stars: ✭ 222 (+335.29%)
Mutual labels:  yolo, yolov5
YOLOv4MLNet
Use the YOLO v4 and v5 (ONNX) models for object detection in C# using ML.Net
Stars: ✭ 61 (+19.61%)
Mutual labels:  yolo, yolov5
ffcnn
ffcnn is a cnn neural network inference framework, written in 600 lines C language.
Stars: ✭ 50 (-1.96%)
Mutual labels:  yolo
YoloV5-LibTorch
一个 C++ 版本的 YoloV5 封装库
Stars: ✭ 77 (+50.98%)
Mutual labels:  yolov5
yolov5-deepsort-tensorrt
A c++ implementation of yolov5 and deepsort
Stars: ✭ 207 (+305.88%)
Mutual labels:  yolov5
OpenCvSharpDnnYolo
Yolo With OpenCvSharp Dnn
Stars: ✭ 25 (-50.98%)
Mutual labels:  yolo
object-detection
Object detection on Jetson Nano, Raspberry Pi and Laptop
Stars: ✭ 49 (-3.92%)
Mutual labels:  yolo
yolov5 onnx2caffe
yolov5 onnx caffe
Stars: ✭ 73 (+43.14%)
Mutual labels:  yolov5
Scaled-YOLOv4-TensorRT
Got 100fps on TX2. Got 500fps on GeForce GTX 1660 Ti. If the project is useful to you, please Star it.
Stars: ✭ 169 (+231.37%)
Mutual labels:  yolo
VideoHunter
基于深度学习的视频人脸检测
Stars: ✭ 31 (-39.22%)
Mutual labels:  yolo
YOLOv5-Lite
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
Stars: ✭ 1,230 (+2311.76%)
Mutual labels:  yolov5

🚀 如果有帮助,点个star!

移动端TNN部署,摄像头实时捕获视频流进行检测。

iOS:

  • Xcode 12.4
  • macOS 11.2.3
  • iPhone 6sp 13.5.1

Android:

  • Android Studio 4.1.1
  • Win10 20H2
  • CPU:Qualcomm 710 GPU:Adreno 616

安卓已经增加权限申请,但如果还是闪退请手动确认下相关权限是否允许。

Android

从界面中选择需要测试的模型。

iOS

从界面中选择需要测试的模型。

模型

model android iOS from other
YOLOv5s yes yes Github NCNN
NanoDet yes yes Github NCNN MNN

iOS:

  • 如果缺少模型请从 "android_TNN_Demo\app\src\main\assets" 复制 .tnnproto 和 .tnnmodel 文件到 "iOS_TNN_Demo\TNNDemo\res" 下。
  • iOS如果opencv2.framework有用到也需要重新下载并替换到工程。
  • iOS默认使用的库为scripts/build_ios.sh编译生成。

Android:

  • 由于手机性能、图像尺寸等因素导致FPS在不同手机上相差比较大。该项目主要测试TNN框架的使用,具体模型的转换可以去TNN官方查看转换教程。
  • 由于opencv库太大只保留 arm64-v8a/armeabi-v7a 有需要其它版本的自己去官方下载。
  • AS版本不一样可能编译会有各种问题,如果编译错误无法解决、建议使用AS4.0以上版本尝试一下。

由于TNN官方还处于开发阶段,不同时间版本可能会出现功能异常或速度差距比较大都是正常的(当前版本功能正常,但速度变慢了)。

懒人本地转换(不会上传模型): xxxx -> tnn

轻量级OpenCV:opencv-mobile

🎨 截图

Android iOS

Android

YOLOv5s NanoDet

iOS

YOLOv5s NanoDet

感谢:

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].