地平线旭日X3开发板Object Detection测试调试

旭日X3派具有最高5TOPS的等效算力

(X3M BPU主频1.2GHz、算力5TOS; X3E BPU 主频0.6GHZ，算力3TOPS)，

因此在开发板上可以运行丰富的AI算法。

在系统/app/ai_inference目录下提供了基础算法示例：

01_basic_sample

系统给出的测试程序只能对给定的斑马图片(zebra_cls.jpg)进行检测，

对其进行少许改造、使其能够对给定的任意图片进行检测，

同时能够输出对象分类ID、置信度和对象名称。

修改后的测试程序目录结构如下：

修改要点：

1）将imagenet1000_clsidx_to_labels.tx文件转换成imagenet1000_clsidx_to_labels.json

2) 增加image目录

存储测试图片，本次测试使用以下4张图片

3）修改test_mobilenetv1.py

#!/usr/bin/env python3
from hobot_dnn import pyeasy_dnn as dnn
import numpy as np
import cv2
import sys
import json

def bgr2nv12_opencv(image):
    height, width = image.shape[0], image.shape[1]
    area = height * width
    yuv420p = cv2.cvtColor(image, cv2.COLOR_BGR2YUV_I420).reshape((area * 3 // 2,))
    y = yuv420p[:area]
    uv_planar = yuv420p[area:].reshape((2, area // 4))
    uv_packed = uv_planar.transpose((1, 0)).reshape((area // 2,))

    nv12 = np.zeros_like(yuv420p)
    nv12[:height * width] = y
    nv12[height * width:] = uv_packed
    return nv12

def print_properties(pro):
    print("tensor type:", pro.tensor_type)
    print("data type:", pro.dtype)
    print("layout:", pro.layout)
    print("shape:", pro.shape)


def get_hw(pro):
    if pro.layout == "NCHW":
        return pro.shape[2], pro.shape[3]
    else:
        return pro.shape[1], pro.shape[2]

if __name__ == '__main__':
    
    #input a picture file
    if len(sys.argv) == 1:
        print("please input picture!!!\nusage: test_mobilenetv1.py filename\n")
        exit(1)
    
    filename = sys.argv[1]
    
    #load object classify infomation
    data_base = None
    with open("./imagenet1000_clsidx_to_labels.json", "r") as f:
        data_base = json.load(f)  

    #load inference modle file
    models = dnn.load('../models/mobilenetv1_224x224_nv12.bin')
    
    #load image file and process
    img_file = cv2.imread(filename)
    h, w = get_hw(models[0].inputs[0].properties)
    des_dim = (w, h)
    resized_data = cv2.resize(img_file, des_dim, interpolation=cv2.INTER_AREA)
    nv12_data = bgr2nv12_opencv(resized_data)
    
    #ai inference
    outputs = models[0].forward(nv12_data)
    cls_id = np.argmax(outputs[0].buffer)
    confidence = outputs[0].buffer[0][np.argmax(outputs[0].buffer)]
   
    #print result 
    print("#"*20, "Result", "#"*20)
    print("->Object Class Id: %d" % (cls_id))
    print("->Confidence: %f" % (confidence))
    print("->Object Name: ", (data_base[str(cls_id)]))
    print("#"*48)

测试用例：

1）斑马检测