add yolov8 face demo

docs/doc/en/vision/face_detection.md

@@ -1,29 +1,44 @@
 ---
-title: MaixPy Face Detection and Key Points Detection
+title: MaixPy Face Detection and Keypoint Detection
 ---
 
 ## Introduction
 
-Face detection can be used in many places, such as providing the step of face detection for face recognition, or applications related to face tracking, and more.
+Face detection can be applied in many scenarios, such as providing the face detection step for face recognition, or for face tracking applications, etc.
 
-The face detection provided here can not only detect faces but also detect 5 key points, including two eyes, one nose, and the two corners of a mouth.
+The face detection provided here can not only detect faces but also detect 5 key points, including two eyes, one nose, and two corners of the mouth.
 
 ![face detection](../../assets/face_detection.jpg)
 
 ## Using Face Detection in MaixPy
 
-MaixPy officially provides two face detection models, sourced from the open projects [face detector 1MB with landmark](https://github.com/biubug6/Face-Detector-1MB-with-landmark) and [Retinaface](https://github.com/biubug6/Pytorch_Retinaface).
+MaixPy officially provides three face detection models from the open-source projects [Face Detector 1MB with landmark](https://github.com/biubug6/Face-Detector-1MB-with-landmark), [Retinaface](https://github.com/biubug6/Pytorch_Retinaface), and [YOLOv8-face](https://github.com/derronqi/yolov8-face).
 
-To use them, first download a model, either one as there's not much difference between them:
-* [face detector 1MB with landmark](https://maixhub.com/model/zoo/377)
-* [Retinaface](https://maixhub.com/model/zoo/378)
+All three models can be used. `YOLOv8-face` performs better but is slightly slower, so you can choose based on your testing.
+
+Using `YOLOv8-face` (requires MaixPy version >= 4.3.8):
+
+```python
+from maix import camera, display, image, nn, app
 
-Then copy the model file to your device, see [Using MaixVision](../basic/maixvision.md) for how to copy.
-> The default image contains a file that can be used directly; if not available, you must download it yourself. The downloaded zip package contains multiple resolutions to choose from; the higher the resolution, the more precise but also more time-consuming.
+detector = nn.YOLOv8(model="/root/models/yolov8n_face.mud")
 
-Next, run the code. The following line of commented code is for loading the `Retinaface` model, choose which line of code to use based on the model you downloaded.
+cam = camera.Camera(detector.input_width(), detector.input_height(), detector.input_format())
+dis = display.Display()
+
+while not app.need_exit():
+    img = cam.read()
+    objs = detector.detect(img, conf_th = 0.5, iou_th = 0.45, keypoint_th = 0.5)
+    for obj in objs:
+        img.draw_rect(obj.x, obj.y, obj.w, obj.h, color = image.COLOR_RED)
+        msg = f'{detector.labels[obj.class_id]}: {obj.score:.2f}'
+        img.draw_string(obj.x, obj.y, msg, color = image.COLOR_RED)
+        detector.draw_pose(img, obj.points, 2, image.COLOR_RED)
+    dis.show(img)
+```
 
-> To use this function, MaixPy must >= 4.1.4.
+For the other two models:
+Here, a line of commented-out code is used to load the `Retinaface` model. Choose which line of code to use based on the model you download.
 
 ```python
 from maix import camera, display, image, nn, app
@@ -43,5 +58,11 @@ while not app.need_exit():
         radius = math.ceil(obj.w / 10)
         img.draw_keypoints(obj.points, image.COLOR_RED, size = radius if radius < 5 else 4)
     dis.show(img)
-
 ```
+
+## Model Downloads and Other Resolution Models
+
+Download the models; the compressed package contains multiple resolutions to choose from. Higher resolution models are more accurate but take longer to process:
+* [Face Detector 1MB with landmark](https://maixhub.com/model/zoo/377)
+* [Retinaface](https://maixhub.com/model/zoo/378)
+* [YOLOv8-face](https://maixhub.com/model/zoo/407)

docs/doc/zh/vision/face_detection.md

@@ -13,19 +13,33 @@ title: MaixPy 人脸检测和关键点检测
 
 ## MaixPy 中使用人脸检测
 
-MaixPy 官方提供了两种人脸检测模型，分别来自开源项目 [face detector 1MB with landmark](https://github.com/biubug6/Face-Detector-1MB-with-landmark) 和 [Retinafate](https://github.com/biubug6/Pytorch_Retinaface)。
+MaixPy 官方提供了三种人脸检测模型，分别来自开源项目 [face detector 1MB with landmark](https://github.com/biubug6/Face-Detector-1MB-with-landmark) 和 [Retinafate](https://github.com/biubug6/Pytorch_Retinaface) 以及 [YOLOv8-face](https://github.com/derronqi/yolov8-face)。
 
-要使用需要先下载模型，选择一个即可，两者区别不大：
-* [face detector 1MB with landmark](https://maixhub.com/model/zoo/377)
-* [Retinafate](https://maixhub.com/model/zoo/378)
+这三种模型都可以用，`YOLOv8-face` 效果比较好但是速度略微慢一些，可以自己实际测试选择使用。
+
+使用`YOLOv8-face`：（需要 MaixPy 版本 >= 4.3.8）
 
-然后拷贝模型文件到设备，拷贝方法见 [MaixVision 使用](../basic/maixvision.md)。
-> 默认镜像里面有一个文件，可以直接使用，如果没有则需要你自己下载，而且下载的压缩包里面有多个分辨率可以选择，分辨率越高越精准但耗时更长
+```python
+from maix import camera, display, image, nn, app
 
-然后执行代码，这里有一行被注释了代码是加载`Retinafae`模型，根据你下载的模型选择使用哪一行代码
+detector = nn.YOLOv8(model="/root/models/yolov8n_face.mud")
 
-> 本功能需要 MaixPy >= 4.1.4 才能使用
+cam = camera.Camera(detector.input_width(), detector.input_height(), detector.input_format())
+dis = display.Display()
+
+while not app.need_exit():
+    img = cam.read()
+    objs = detector.detect(img, conf_th = 0.5, iou_th = 0.45, keypoint_th = 0.5)
+    for obj in objs:
+        img.draw_rect(obj.x, obj.y, obj.w, obj.h, color = image.COLOR_RED)
+        msg = f'{detector.labels[obj.class_id]}: {obj.score:.2f}'
+        img.draw_string(obj.x, obj.y, msg, color = image.COLOR_RED)
+        detector.draw_pose(img, obj.points, 2, image.COLOR_RED)
+    dis.show(img)
+```
 
+另外两种模型使用方法：
+这里有一行被注释了代码是加载`Retinafae`模型，根据你下载的模型选择使用哪一行代码
 
 ```python
 from maix import camera, display, image, nn, app
@@ -49,6 +63,13 @@ while not app.need_exit():
 
 ```
 
+## 模型下载和其它分辨率模型
+
+下载模型，下载的压缩包里面有多个分辨率可以选择，分辨率越高越精准但耗时更长：
+* [face detector 1MB with landmark](https://maixhub.com/model/zoo/377)
+* [Retinafate](https://maixhub.com/model/zoo/378)
+* [YOLOv8-face](https://maixhub.com/model/zoo/407)
+
 
 
 

examples/vision/ai_vision/nn_yolov8_face.py

@@ -0,0 +1,16 @@
+from maix import camera, display, image, nn, app
+
+detector = nn.YOLOv8(model="/root/models/yolov8n_face.mud")
+
+cam = camera.Camera(detector.input_width(), detector.input_height(), detector.input_format())
+dis = display.Display()
+
+while not app.need_exit():
+    img = cam.read()
+    objs = detector.detect(img, conf_th = 0.5, iou_th = 0.45, keypoint_th = 0.5)
+    for obj in objs:
+        img.draw_rect(obj.x, obj.y, obj.w, obj.h, color = image.COLOR_RED)
+        msg = f'{detector.labels[obj.class_id]}: {obj.score:.2f}'
+        img.draw_string(obj.x, obj.y, msg, color = image.COLOR_RED)
+        detector.draw_pose(img, obj.points, 2, image.COLOR_RED)
+    dis.show(img)