🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署,支持Android与iOS。
iOS
Select the model to be tested directly on the interface.
Android
Select the model to be tested directly on the interface.
model | android | iOS | from | other |
---|---|---|---|---|
YOLOv5s | yes | yes | Github | TNN |
YOLOv4-tiny | yes | yes | Github | |
YOLOv3-nano | yes | yes | Github | |
YOLOv5s_custom_op | yes | yes | zhihu | |
NanoDet | yes | yes | Github | TNN MNN |
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 | yes | Github |
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
:art: 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 |
---|---|---|
chineseocr_lite_01 | chineseocr_lite_02 | light_openpose |
---|---|---|
yolact | yoloface500k-landmark106 | dbface |
---|---|---|
Thanks: