cmdbug / Yolov5_ncnn
Licence: gpl-3.0
🍅 Deploy NCNN on mobile phones. Support Android and iOS. 移动端NCNN部署,支持Android与iOS。
Stars: ✭ 535
Projects that are alternatives of or similar to Yolov5 ncnn
Tensornets
High level network definitions with pre-trained weights in TensorFlow
Stars: ✭ 982 (+83.55%)
Mutual labels: object-detection, yolo, yolov3, mobilenet
Keras Yolov3 Mobilenet
I transfer the backend of yolov3 into Mobilenetv1,VGG16,ResNet101 and ResNeXt101
Stars: ✭ 552 (+3.18%)
Mutual labels: object-detection, yolo, yolov3, mobilenet
Pine
🌲 Aimbot powered by real-time object detection with neural networks, GPU accelerated with Nvidia. Optimized for use with CS:GO.
Stars: ✭ 202 (-62.24%)
Mutual labels: object-detection, yolo, yolov3, detection
Yolo label
GUI for marking bounded boxes of objects in images for training neural network Yolo v3 and v2 https://github.com/AlexeyAB/darknet, https://github.com/pjreddie/darknet
Stars: ✭ 128 (-76.07%)
Mutual labels: object-detection, yolo, yolov3, detection
Yolodet Pytorch
reproduce the YOLO series of papers in pytorch, including YOLOv4, PP-YOLO, YOLOv5,YOLOv3, etc.
Stars: ✭ 206 (-61.5%)
Mutual labels: object-detection, yolo, yolov3
Yolov3 Tf2
YoloV3 Implemented in Tensorflow 2.0
Stars: ✭ 2,327 (+334.95%)
Mutual labels: object-detection, yolo, yolov3
Yolo3 4 Py
A Python wrapper on Darknet. Compatible with YOLO V3.
Stars: ✭ 504 (-5.79%)
Mutual labels: object-detection, yolo, yolov3
Object Detection
Object detection with ssd_mobilenet and tiny-yolo (Add: YOLOv3, tflite)
Stars: ✭ 173 (-67.66%)
Mutual labels: object-detection, yolov3, detection
object-tracking
Multiple Object Tracking System in Keras + (Detection Network - YOLO)
Stars: ✭ 89 (-83.36%)
Mutual labels: detection, yolo, yolov3
Pytorch Yolo V3
A PyTorch implementation of the YOLO v3 object detection algorithm
Stars: ✭ 3,148 (+488.41%)
Mutual labels: object-detection, yolo, yolov3
Tensorflow object tracking video
Object Tracking in Tensorflow ( Localization Detection Classification ) developed to partecipate to ImageNET VID competition
Stars: ✭ 491 (-8.22%)
Mutual labels: object-detection, yolo, detection
Object Detection Api
Yolov3 Object Detection implemented as APIs, using TensorFlow and Flask
Stars: ✭ 177 (-66.92%)
Mutual labels: object-detection, yolo, yolov3
Yolo v3 tutorial from scratch
Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"
Stars: ✭ 2,192 (+309.72%)
Mutual labels: object-detection, yolo, yolov3
Deep Sort Yolov4
People detection and optional tracking with Tensorflow backend.
Stars: ✭ 306 (-42.8%)
Mutual labels: object-detection, yolo, yolov3
yolo3 tensorflow
yolo3 implement by tensorflow, including mobilenet_v1, mobilenet_v2
Stars: ✭ 48 (-91.03%)
Mutual labels: detection, mobilenet, yolov3
Alturos.yolo
C# Yolo Darknet Wrapper (real-time object detection)
Stars: ✭ 308 (-42.43%)
Mutual labels: object-detection, yolo, yolov3
Rectlabel Support
RectLabel - An image annotation tool to label images for bounding box object detection and segmentation.
Stars: ✭ 338 (-36.82%)
Mutual labels: object-detection, yolo, detection
Tfjs Yolo Tiny
In-Browser Object Detection using Tiny YOLO on Tensorflow.js
Stars: ✭ 465 (-13.08%)
Mutual labels: object-detection, yolo, detection
Bmw Labeltool Lite
This repository provides you with a easy to use labeling tool for State-of-the-art Deep Learning training purposes.
Stars: ✭ 145 (-72.9%)
Mutual labels: object-detection, yolo, yolov3
🚀 If it helps you, click a star! ⭐️
Ncnn deployment on mobile,support:YOLOv5s,YOLOv4-tiny,MobileNetV2-YOLOv3-nano,Simple-Pose,Yolact,ChineseOCR-lite,ENet,Landmark106,DBFace,MBNv2-FCN and MBNv3-Seg-small on camera.
iOS:
- Xcode 12.4
- macOS 11.2.3
- iPhone 6sp 13.5.1
Android:
- Android Studio 4.1
- Win10 20H2
- Meizu 16x 8.1.0 (CPU:Qualcomm 710 GPU:Adreno 616)
Android has added permission requests, but if it still crashes, please manually confirm whether the relevant permissions are allowed.
iOS
Select the model to be tested directly on the interface.
Android
Select the model to be tested directly on the interface.
Models
model | android | iOS | from |
---|---|---|---|
YOLOv5s | yes | yes | Github |
YOLOv4-tiny | yes | yes | Github |
YOLOv3-nano | yes | yes | Github |
YOLOv5s_custom_op | yes | yes | zhihu |
NanoDet | yes | yes | Github |
YOLO-Fastest-xl | yes | yes | Github |
Simple-Pose | yes | yes | Github |
Yolact | yes | yes | Github zhihu |
ChineseOCR_lite | yes | yes | Github zhihu |
ENet | bug | cancel | Github |
Landmark106 | yes | yes | Github |
DBFace | yes | yes | Github |
MBNv2-FCN | yes | yes | Github |
MBNv3-Seg-small | yes | yes | Github |
Light_OpenPose | yes | TODO | Github |
iOS:
- Copy .param and .bin from "android_YOLOV5_NCNN\app\src\main\assets" to "iOS_YOLOv5NCNN\YOLOv5NCNN\res"
- If it prompts that net.h can't be found, you need to download it from the ncnn official website or compile .framework(20201208) yourself and replace it in the project. If opencv2.framework(4.3.0) is useful, you need to download it again and replace it in the project.
- The default library used by iOS does not include vulkan and bitcode.
- Normally, you need to re-download ncnn.framework/glslang.framework/openmp.framework/opencv2.framework and replace it with the project.
- For the configuration of Vulkan, please refer to the general configuration mentioned in Issues.
Android:
- Due to factors such as mobile phone performance and image size, FPS varies greatly on different mobile phones. This project mainly tests the use of the NCNN framework. For the conversion of specific models, you can go to the NCNN official to view the conversion tutorial.
- Because the opencv library is too large, only arm64-v8a/armeabi-v7a is reserved. If you need other versions, go to the official download.
- ncnn temporarily uses the vulkan version, and acceleration needs to be turned on before loading, which is not turned on in this project. If you want to use the ncnn version, you need to modify the CMakeLists.txt configuration.
- Different AS versions may have various problems with compilation. If the compilation error cannot be solved, it is recommended to use AS4.0 or higher to try.
This project is more about practicing the use and deployment of various models, without too much processing in terms of speed. If you have requirements for speed, you can directly obtain data such as YUV for direct input or use methods such as texture and opengl to achieve data input, reducing intermediate data transmission and conversion.
Convert locally(Will not upload model): xxxx -> ncnn
Minimal OpenCV:opencv-mobile
🎨 Screenshot
Android | iOS |
---|---|
Android
mbnv2-yolov3-nano | yolov4-tiny | yolov5s |
---|---|---|
simple_pose | yolact | chineseocr_lite_01 |
---|---|---|
chineseocr_lite_02 | ENet | yoloface500k-landmark106 |
---|---|---|
dbface | mbnv2_fcn | mbnv3_seg_small |
---|---|---|
yolov5s_custom_op | nanodet | yolo-fastest-xl |
---|---|---|
light_openpose |
---|
iOS
mbnv2-yolov3-nano | yolov4-tiny | yolov5s |
---|---|---|
yolov5s_custom_op | nanodet | yolo-fastest-xl |
---|---|---|
mbnv2_fcn | mbnv3_seg_small | simple_pose |
---|---|---|
yolact | yoloface500k-landmark106 | dbface |
---|---|---|
chineseocr_lite_01 | chineseocr_lite_02 | light_openpose |
---|---|---|
TODO |
Thanks:
- sunnyden, dog-qiuqiu, ..., nihui
- https://github.com/Tencent/ncnn
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].