K230/main.py.autosave at main · yangnianboy/K230 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
from libs.PipeLine import PipeLine, ScopedTiming
from libs.AIBase import AIBase
from libs.AI2D import Ai2d
from libs.Utils import *
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YOLOv8检测类
class ObjectDetectionApp(AIBase):
    def __init__(self,kmodel_path,labels,model_input_size,max_boxes_num,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)
        self.kmodel_path=kmodel_path
        self.labels=labels
        # 模型输入分辨率
        self.model_input_size=model_input_size
        # 阈值设置
        self.confidence_threshold=confidence_threshold
        self.nms_threshold=nms_threshold
        self.max_boxes_num=max_boxes_num
        # sensor给到AI的图像分辨率
        self.rgb888p_size=[ALIGN_UP(rgb888p_size[0],16),rgb888p_size[1]]
        # 显示分辨率
        self.display_size=[ALIGN_UP(display_size[0],16),display_size[1]]
        self.debug_mode=debug_mode
        # 检测框预置颜色值
        self.color_four=get_colors(len(self.labels))
        # 宽高缩放比例
        self.x_factor = float(self.rgb888p_size[0])/self.model_input_size[0]
        self.y_factor = float(self.rgb888p_size[1])/self.model_input_size[1]
        # 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，您可以通过设置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
            top,bottom,left,right,self.scale=letterbox_pad_param(self.rgb888p_size,self.model_input_size)
            # 配置padding预处理
            self.ai2d.pad([0,0,0,0,top,bottom,left,right], 0, [128,128,128])
            self.ai2d.resize(nn.interp_method.tf_bilinear, nn.interp_mode.half_pixel)
            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]])

    def preprocess(self,input_np):
        with ScopedTiming("preprocess",self.debug_mode > 0):
            return [nn.from_numpy(input_np)]

    # 自定义当前任务的后处理
    def postprocess(self,results):
        with ScopedTiming("postprocess",self.debug_mode > 0):
            new_result=results[0][0].transpose()
            det_res = aidemo.yolov8_det_postprocess(new_result.copy(),[self.rgb888p_size[1],self.rgb888p_size[0]],[self.model_input_size[1],self.model_input_size[0]],[self.display_size[1],self.display_size[0]],len(self.labels),self.confidence_threshold,self.nms_threshold,self.max_boxes_num)
            return det_res

    # 绘制结果
    def draw_result(self,pl,dets):
        with ScopedTiming("display_draw",self.debug_mode >0):
            if dets:
                pl.osd_img.clear()
                for i in range(len(dets[0])):
                    x, y, w, h = map(lambda x: int(round(x, 0)), dets[0][i])
                    pl.osd_img.draw_rectangle(x,y, w, h, color=self.color_four[dets[1][i]],thickness=4)
                    pl.osd_img.draw_string_advanced( x , y-50,32," " + self.labels[dets[1][i]] + " " + str(round(dets[2][i],2)) , color=self.color_four[dets[1][i]])
            else:
                pl.osd_img.clear()


if __name__=="__main__":
    # 显示模式，默认"hdmi",可以选择"hdmi"和"lcd"
    display_mode="lcd"
    rgb888p_size=[224,224]

    if display_mode=="hdmi":
        display_size=[1920,1080]
    else:
        display_size=[800,480]
    # 模型路径
    kmodel_path="/sdcard/examples/kmodel/yolov8n_224.kmodel"
    labels = ["person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch", "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"]
    # 其它参数设置
    confidence_threshold = 0.5
    nms_threshold = 0.4
    max_boxes_num = 30

    # 初始化PipeLine
    pl=PipeLine(rgb888p_size=rgb888p_size,display_size=display_size,display_mode=display_mode)
    pl.create()
    # 初始化自定义目标检测实例
    ob_det=ObjectDetectionApp(kmodel_path,labels=labels,model_input_size=[224,224],max_boxes_num=max_boxes_num,confidence_threshold=confidence_threshold,nms_threshold=nms_threshold,rgb888p_size=rgb888p_size,display_size=display_size,debug_mode=0)
    ob_det.config_preprocess()
    while True:
        with ScopedTiming("total",1):
            # 获取当前帧数据
            img=pl.get_frame()
            # 推理当前帧
            res=ob_det.run(img)
            # 绘制结果到PipeLine的osd图像
            ob_det.draw_result(pl,res)
            # 显示当前的绘制结果
            pl.show_image()
            gc.collect()
    ob_det.deinit()
    pl.destroy()