update examples

Signed-off-by: huangziyi <[email protected]>

share/qtcreator/examples/04-AI-Demo/eye_gaze.py

@@ -0,0 +1,229 @@
+from libs.PipeLine import PipeLine, ScopedTiming
+from libs.AIBase import AIBase
+from libs.AI2D import Ai2d
+import os
+import ujson
+from media.media import *
+from time import *
+import nncase_runtime as nn
+import ulab.numpy as np
+import time
+import image
+import aidemo
+import random
+import gc
+import sys
+import math
+
+# 自定义人脸检测任务类
+class FaceDetApp(AIBase):
+    def __init__(self,kmodel_path,model_input_size,anchors,confidence_threshold=0.25,nms_threshold=0.3,rgb888p_size=[1280,720],display_size=[1920,1080],debug_mode=0):
+        super().__init__(kmodel_path,model_input_size,rgb888p_size,debug_mode)
+        # kmodel路径
+        self.kmodel_path=kmodel_path
+        # 检测模型输入分辨率
+        self.model_input_size=model_input_size
+        # 置信度阈值
+        self.confidence_threshold=confidence_threshold
+        # nms阈值
+        self.nms_threshold=nms_threshold
+        self.anchors=anchors
+        # sensor给到AI的图像分辨率，宽16字节对齐
+        self.rgb888p_size=[ALIGN_UP(rgb888p_size[0],16),rgb888p_size[1]]
+        # 视频输出VO分辨率，宽16字节对齐
+        self.display_size=[ALIGN_UP(display_size[0],16),display_size[1]]
+        # debug模式
+        self.debug_mode=debug_mode
+        # Ai2d实例，用于实现模型预处理
+        self.ai2d=Ai2d(debug_mode)
+        # 设置Ai2d的输入输出格式和类型
+        self.ai2d.set_ai2d_dtype(nn.ai2d_format.NCHW_FMT,nn.ai2d_format.NCHW_FMT,np.uint8, np.uint8)
+
+    # 配置预处理操作，这里使用了padding和resize，Ai2d支持crop/shift/pad/resize/affine，具体代码请打开/sdcard/app/libs/AI2D.py查看
+    def config_preprocess(self,input_image_size=None):
+        with ScopedTiming("set preprocess config",self.debug_mode > 0):
+            # 初始化ai2d预处理配置，默认为sensor给到AI的尺寸，可以通过设置input_image_size自行修改输入尺寸
+            ai2d_input_size=input_image_size if input_image_size else self.rgb888p_size
+            # 设置padding预处理
+            self.ai2d.pad(self.get_pad_param(), 0, [104,117,123])
+            # 设置resize预处理
+            self.ai2d.resize(nn.interp_method.tf_bilinear, nn.interp_mode.half_pixel)
+            # 构建预处理流程,参数为预处理输入tensor的shape和预处理输出的tensor的shape
+            self.ai2d.build([1,3,ai2d_input_size[1],ai2d_input_size[0]],[1,3,self.model_input_size[1],self.model_input_size[0]])
+
+    # 自定义任务后处理,这里使用了aidemo库的face_det_post_process接口
+    def postprocess(self,results):
+        with ScopedTiming("postprocess",self.debug_mode > 0):
+            res = aidemo.face_det_post_process(self.confidence_threshold,self.nms_threshold,self.model_input_size[0],self.anchors,self.rgb888p_size,results)
+            if len(res)==0:
+                return res
+            else:
+                return res[0]
+
+    # 计算padding参数
+    def get_pad_param(self):
+        dst_w = self.model_input_size[0]
+        dst_h = self.model_input_size[1]
+        # 计算最小的缩放比例，等比例缩放
+        ratio_w = dst_w / self.rgb888p_size[0]
+        ratio_h = dst_h / self.rgb888p_size[1]
+        if ratio_w < ratio_h:
+            ratio = ratio_w
+        else:
+            ratio = ratio_h
+        new_w = (int)(ratio * self.rgb888p_size[0])
+        new_h = (int)(ratio * self.rgb888p_size[1])
+        dw = (dst_w - new_w) / 2
+        dh = (dst_h - new_h) / 2
+        top = (int)(round(0))
+        bottom = (int)(round(dh * 2 + 0.1))
+        left = (int)(round(0))
+        right = (int)(round(dw * 2 - 0.1))
+        return [0,0,0,0,top, bottom, left, right]
+
+# 自定义注视估计任务类
+class EyeGazeApp(AIBase):
+    def __init__(self,kmodel_path,model_input_size,rgb888p_size=[1920,1080],display_size=[1920,1080],debug_mode=0):
+        super().__init__(kmodel_path,model_input_size,rgb888p_size,debug_mode)
+        # kmodel路径
+        self.kmodel_path=kmodel_path
+        # 注视估计模型输入分辨率
+        self.model_input_size=model_input_size
+        # sensor给到AI的图像分辨率，宽16字节对齐
+        self.rgb888p_size=[ALIGN_UP(rgb888p_size[0],16),rgb888p_size[1]]
+        # 视频输出VO分辨率，宽16字节对齐
+        self.display_size=[ALIGN_UP(display_size[0],16),display_size[1]]
+        # debug模式
+        self.debug_mode=debug_mode
+        # Ai2d实例，用于实现模型预处理
+        self.ai2d=Ai2d(debug_mode)
+        # 设置Ai2d的输入输出格式和类型
+        self.ai2d.set_ai2d_dtype(nn.ai2d_format.NCHW_FMT,nn.ai2d_format.NCHW_FMT,np.uint8, np.uint8)
+
+    # 配置预处理操作，这里使用了crop和resize，Ai2d支持crop/shift/pad/resize/affine，具体代码请打开/sdcard/app/libs/AI2D.py查看
+    def config_preprocess(self,det,input_image_size=None):
+        with ScopedTiming("set preprocess config",self.debug_mode > 0):
+            # 初始化ai2d预处理配置
+            ai2d_input_size=input_image_size if input_image_size else self.rgb888p_size
+            # 计算crop预处理参数
+            x, y, w, h = map(lambda x: int(round(x, 0)), det[:4])
+            # 设置crop预处理
+            self.ai2d.crop(x,y,w,h)
+            # 设置resize预处理
+            self.ai2d.resize(nn.interp_method.tf_bilinear, nn.interp_mode.half_pixel)
+            # 构建预处理流程,参数为预处理输入tensor的shape和预处理输出的tensor的shape
+            self.ai2d.build([1,3,ai2d_input_size[1],ai2d_input_size[0]],[1,3,self.model_input_size[1],self.model_input_size[0]])
+
+    # 自定义后处理，results是模型输出的array列表，这里调用了aidemo库的eye_gaze_post_process接口
+    def postprocess(self,results):
+        with ScopedTiming("postprocess",self.debug_mode > 0):
+            post_ret = aidemo.eye_gaze_post_process(results)
+            return post_ret[0],post_ret[1]
+
+# 自定义注视估计类
+class EyeGaze:
+    def __init__(self,face_det_kmodel,eye_gaze_kmodel,det_input_size,eye_gaze_input_size,anchors,confidence_threshold=0.25,nms_threshold=0.3,rgb888p_size=[1920,1080],display_size=[1920,1080],debug_mode=0):
+        # 人脸检测模型路径
+        self.face_det_kmodel=face_det_kmodel
+        # 人脸注视估计模型路径
+        self.eye_gaze_kmodel=eye_gaze_kmodel
+        # 人脸检测模型输入分辨率
+        self.det_input_size=det_input_size
+        # 人脸注视估计模型输入分辨率
+        self.eye_gaze_input_size=eye_gaze_input_size
+        # anchors
+        self.anchors=anchors
+        # 置信度阈值
+        self.confidence_threshold=confidence_threshold
+        # nms阈值
+        self.nms_threshold=nms_threshold
+        # sensor给到AI的图像分辨率，宽16字节对齐
+        self.rgb888p_size=[ALIGN_UP(rgb888p_size[0],16),rgb888p_size[1]]
+        # 视频输出VO分辨率，宽16字节对齐
+        self.display_size=[ALIGN_UP(display_size[0],16),display_size[1]]
+        # debug_mode模式
+        self.debug_mode=debug_mode
+        # 人脸检测实例
+        self.face_det=FaceDetApp(self.face_det_kmodel,model_input_size=self.det_input_size,anchors=self.anchors,confidence_threshold=self.confidence_threshold,nms_threshold=self.nms_threshold,rgb888p_size=self.rgb888p_size,display_size=self.display_size,debug_mode=0)
+        # 注视估计实例
+        self.eye_gaze=EyeGazeApp(self.eye_gaze_kmodel,model_input_size=self.eye_gaze_input_size,rgb888p_size=self.rgb888p_size,display_size=self.display_size)
+        # 人脸检测配置预处理
+        self.face_det.config_preprocess()
+
+    #run方法
+    def run(self,input_np):
+        # 先进行人脸检测
+        det_boxes=self.face_det.run(input_np)
+        eye_gaze_res=[]
+        for det_box in det_boxes:
+            # 对每一个检测到的人脸做注视估计
+            self.eye_gaze.config_preprocess(det_box)
+            pitch,yaw=self.eye_gaze.run(input_np)
+            eye_gaze_res.append((pitch,yaw))
+        return det_boxes,eye_gaze_res
+
+    # 绘制注视估计效果
+    def draw_result(self,pl,dets,eye_gaze_res):
+        pl.osd_img.clear()
+        if dets:
+            for det,gaze_ret in zip(dets,eye_gaze_res):
+                pitch , yaw = gaze_ret
+                length = self.display_size[0]/ 2
+                x, y, w, h = map(lambda x: int(round(x, 0)), det[:4])
+                x = x * self.display_size[0] // self.rgb888p_size[0]
+                y = y * self.display_size[1] // self.rgb888p_size[1]
+                w = w * self.display_size[0] // self.rgb888p_size[0]
+                h = h * self.display_size[1] // self.rgb888p_size[1]
+                center_x = (x + w / 2.0)
+                center_y = (y + h / 2.0)
+                dx = -length * math.sin(pitch) * math.cos(yaw)
+                target_x = int(center_x + dx)
+                dy = -length * math.sin(yaw)
+                target_y = int(center_y + dy)
+                pl.osd_img.draw_arrow(int(center_x), int(center_y), target_x, target_y, color = (255,255,0,0), size = 30, thickness = 2)
+
+
+if __name__=="__main__":
+    # 显示模式，默认"hdmi",可以选择"hdmi"和"lcd"
+    display_mode="hdmi"
+    if display_mode=="hdmi":
+        display_size=[1920,1080]
+    else:
+        display_size=[800,480]
+    # 人脸检测模型路径
+    face_det_kmodel_path="/sdcard/app/tests/kmodel/face_detection_320.kmodel"
+    # 人脸注视估计模型路径
+    eye_gaze_kmodel_path="/sdcard/app/tests/kmodel/eye_gaze.kmodel"
+    # 其他参数
+    anchors_path="/sdcard/app/tests/utils/prior_data_320.bin"
+    rgb888p_size=[1920,1080]
+    face_det_input_size=[320,320]
+    eye_gaze_input_size=[448,448]
+    confidence_threshold=0.5
+    nms_threshold=0.2
+    anchor_len=4200
+    det_dim=4
+    anchors = np.fromfile(anchors_path, dtype=np.float)
+    anchors = anchors.reshape((anchor_len,det_dim))
+
+    # 初始化PipeLine，只关注传给AI的图像分辨率，显示的分辨率
+    pl=PipeLine(rgb888p_size=rgb888p_size,display_size=display_size,display_mode=display_mode)
+    pl.create()
+    eg=EyeGaze(face_det_kmodel_path,eye_gaze_kmodel_path,det_input_size=face_det_input_size,eye_gaze_input_size=eye_gaze_input_size,anchors=anchors,confidence_threshold=confidence_threshold,nms_threshold=nms_threshold,rgb888p_size=rgb888p_size,display_size=display_size)
+    try:
+        while True:
+            os.exitpoint()
+            with ScopedTiming("total",1):
+                img=pl.get_frame()                          # 获取当前帧
+                det_boxes,eye_gaze_res=eg.run(img)          # 推理当前帧
+                eg.draw_result(pl,det_boxes,eye_gaze_res)   # 绘制推理效果
+                pl.show_image()                             # 展示推理效果
+                gc.collect()
+    except Exception as e:
+        sys.print_exception(e)
+    finally:
+        eg.face_det.deinit()
+        eg.eye_gaze.deinit()
+        pl.destroy()
+
+

share/qtcreator/examples/04-AI-Demo/face_detection.py

@@ -0,0 +1,124 @@
+from libs.PipeLine import PipeLine, ScopedTiming
+from libs.AIBase import AIBase
+from libs.AI2D import Ai2d
+import os
+import ujson
+from media.media import *
+from time import *
+import nncase_runtime as nn
+import ulab.numpy as np
+import time
+import utime
+import image
+import random
+import gc
+import sys
+import aidemo
+
+# 自定义人脸检测类，继承自AIBase基类
+class FaceDetectionApp(AIBase):
+    def __init__(self, kmodel_path, model_input_size, anchors, confidence_threshold=0.5, nms_threshold=0.2, rgb888p_size=[224,224], display_size=[1920,1080], debug_mode=0):
+        super().__init__(kmodel_path, model_input_size, rgb888p_size, debug_mode)  # 调用基类的构造函数
+        self.kmodel_path = kmodel_path  # 模型文件路径
+        self.model_input_size = model_input_size  # 模型输入分辨率
+        self.confidence_threshold = confidence_threshold  # 置信度阈值
+        self.nms_threshold = nms_threshold  # NMS（非极大值抑制）阈值
+        self.anchors = anchors  # 锚点数据，用于目标检测
+        self.rgb888p_size = [ALIGN_UP(rgb888p_size[0], 16), rgb888p_size[1]]  # sensor给到AI的图像分辨率，并对宽度进行16的对齐
+        self.display_size = [ALIGN_UP(display_size[0], 16), display_size[1]]  # 显示分辨率，并对宽度进行16的对齐
+        self.debug_mode = debug_mode  # 是否开启调试模式
+        self.ai2d = Ai2d(debug_mode)  # 实例化Ai2d，用于实现模型预处理
+        self.ai2d.set_ai2d_dtype(nn.ai2d_format.NCHW_FMT, nn.ai2d_format.NCHW_FMT, np.uint8, np.uint8)  # 设置Ai2d的输入输出格式和类型
+
+    # 配置预处理操作，这里使用了pad和resize，Ai2d支持crop/shift/pad/resize/affine，具体代码请打开/sdcard/app/libs/AI2D.py查看
+    def config_preprocess(self, input_image_size=None):
+        with ScopedTiming("set preprocess config", self.debug_mode > 0):  # 计时器，如果debug_mode大于0则开启
+            ai2d_input_size = input_image_size if input_image_size else self.rgb888p_size  # 初始化ai2d预处理配置，默认为sensor给到AI的尺寸，可以通过设置input_image_size自行修改输入尺寸
+            top, bottom, left, right = self.get_padding_param()  # 获取padding参数
+            self.ai2d.pad([0, 0, 0, 0, top, bottom, left, right], 0, [104, 117, 123])  # 填充边缘
+            self.ai2d.resize(nn.interp_method.tf_bilinear, nn.interp_mode.half_pixel)  # 缩放图像
+            self.ai2d.build([1,3,ai2d_input_size[1],ai2d_input_size[0]],[1,3,self.model_input_size[1],self.model_input_size[0]])  # 构建预处理流程
+
+    # 自定义当前任务的后处理，results是模型输出array列表，这里使用了aidemo库的face_det_post_process接口
+    def postprocess(self, results):
+        with ScopedTiming("postprocess", self.debug_mode > 0):
+            post_ret = aidemo.face_det_post_process(self.confidence_threshold, self.nms_threshold, self.model_input_size[1], self.anchors, self.rgb888p_size, results)
+            if len(post_ret) == 0:
+                return post_ret
+            else:
+                return post_ret[0]
+
+    # 绘制检测结果到画面上
+    def draw_result(self, pl, dets):
+        with ScopedTiming("display_draw", self.debug_mode > 0):
+            if dets:
+                pl.osd_img.clear()  # 清除OSD图像
+                for det in dets:
+                    # 将检测框的坐标转换为显示分辨率下的坐标
+                    x, y, w, h = map(lambda x: int(round(x, 0)), det[:4])
+                    x = x * self.display_size[0] // self.rgb888p_size[0]
+                    y = y * self.display_size[1] // self.rgb888p_size[1]
+                    w = w * self.display_size[0] // self.rgb888p_size[0]
+                    h = h * self.display_size[1] // self.rgb888p_size[1]
+                    pl.osd_img.draw_rectangle(x, y, w, h, color=(255, 255, 0, 255), thickness=2)  # 绘制矩形框
+            else:
+                pl.osd_img.clear()
+
+    # 获取padding参数
+    def get_padding_param(self):
+        dst_w = self.model_input_size[0]  # 模型输入宽度
+        dst_h = self.model_input_size[1]  # 模型输入高度
+        ratio_w = dst_w / self.rgb888p_size[0]  # 宽度缩放比例
+        ratio_h = dst_h / self.rgb888p_size[1]  # 高度缩放比例
+        ratio = min(ratio_w, ratio_h)  # 取较小的缩放比例
+        new_w = int(ratio * self.rgb888p_size[0])  # 新宽度
+        new_h = int(ratio * self.rgb888p_size[1])  # 新高度
+        dw = (dst_w - new_w) / 2  # 宽度差
+        dh = (dst_h - new_h) / 2  # 高度差
+        top = int(round(0))
+        bottom = int(round(dh * 2 + 0.1))
+        left = int(round(0))
+        right = int(round(dw * 2 - 0.1))
+        return top, bottom, left, right
+
+if __name__ == "__main__":
+    # 显示模式，默认"hdmi",可以选择"hdmi"和"lcd"
+    display_mode="hdmi"
+    if display_mode=="hdmi":
+        display_size=[1920,1080]
+    else:
+        display_size=[800,480]
+    # 设置模型路径和其他参数
+    kmodel_path = "/sdcard/app/tests/kmodel/face_detection_320.kmodel"
+    # 其它参数
+    confidence_threshold = 0.5
+    nms_threshold = 0.2
+    anchor_len = 4200
+    det_dim = 4
+    anchors_path = "/sdcard/app/tests/utils/prior_data_320.bin"
+    anchors = np.fromfile(anchors_path, dtype=np.float)
+    anchors = anchors.reshape((anchor_len, det_dim))
+    rgb888p_size = [1920, 1080]
+
+    # 初始化PipeLine，用于图像处理流程
+    pl = PipeLine(rgb888p_size=rgb888p_size, display_size=display_size, display_mode=display_mode)
+    pl.create()  # 创建PipeLine实例
+    # 初始化自定义人脸检测实例
+    face_det = FaceDetectionApp(kmodel_path, model_input_size=[320, 320], anchors=anchors, confidence_threshold=confidence_threshold, nms_threshold=nms_threshold, rgb888p_size=rgb888p_size, display_size=display_size, debug_mode=0)
+    face_det.config_preprocess()  # 配置预处理
+
+    try:
+        while True:
+            os.exitpoint()                      # 检查是否有退出信号
+            with ScopedTiming("total",1):
+                img = pl.get_frame()            # 获取当前帧数据
+                res = face_det.run(img)         # 推理当前帧
+                face_det.draw_result(pl, res)   # 绘制结果
+                pl.show_image()                 # 显示结果
+                gc.collect()                    # 垃圾回收
+    except Exception as e:
+        sys.print_exception(e)                  # 打印异常信息
+    finally:
+        face_det.deinit()                       # 反初始化
+        pl.destroy()                            # 销毁PipeLine实例
+