/YOLOv5_NCNN

🍅 Ncnn deployment on mobile,support:YOLOv5s,YOLOv4-tiny,MobileNetV2-YOLOv3-nano,Simple-Pose,Yolact,ChineseOCR-lite,ENet,Landmark106,DBFace,MBNv2-FCN,MBNv3-Seg-small and NanoDet on camera.

Primary LanguageC++GNU General Public License v3.0GPL-3.0

中文说明

🚀 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 11.5
  • macOS 10.15.4
  • iPhone 6sp 13.5.1

Android:

  • Android Studio 4.0
  • Win10 1909
  • 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
Simple-Pose yes coming soon Github
Yolact yes coming soon Github zhihu
ChineseOCR_lite yes probably Github zhihu
ENet yes cancel Github
Landmark106 yes coming soon Github
DBFace yes coming soon Github
MBNv2-FCN yes coming soon Github
MBNv3-Seg-small yes coming soon Github
YOLOv5s_custom_op yes coming soon zhihu
NanoDet yes yes Github
YOLO-Fastest-xl yes bug Github

Note:

  • 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.

🎨 Screenshot

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
none none none

iOS

mbnv2-yolov3-nano yolov4-tiny yolov5s
xxx nanodet yolo-fastest-xl
xxx none none

Thanks: