2024年最新YOLO-V3 训练Kitti数据集_yolo训练kitti(1)，2024年最新五面阿里拿下飞猪事业部offer

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上C C++开发知识点，真正体系化！

由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新

如果你需要这些资料，可以戳这里获取

from ctypes import \*
import math
import random
#import module named cv2 to draw
import cv2
from PIL import Image


def sample(probs):
    s = sum(probs)
    probs = [a/s for a in probs]
    r = random.uniform(0, 1)
    for i in range(len(probs)):
        r = r - probs[i]
        if r <= 0:
            return i
    return len(probs)-1
 
def c\_array(ctype, values):
    arr = (ctype\*len(values))()
    arr[:] = values
    return arr
 
class BOX(Structure):
    _fields_ = [("x", c_float),
                ("y", c_float),
                ("w", c_float),
                ("h", c_float)]
 
class DETECTION(Structure):
    _fields_ = [("bbox", BOX),
                ("classes", c_int),
                ("prob", POINTER(c_float)),
                ("mask", POINTER(c_float)),
                ("objectness", c_float),
                ("sort\_class", c_int)]
 
 
class IMAGE(Structure):
    _fields_ = [("w", c_int),
                ("h", c_int),
                ("c", c_int),
                ("data", POINTER(c_float))]
 
class METADATA(Structure):
    _fields_ = [("classes", c_int),
                ("names", POINTER(c_char_p))]
 
    
 
#lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD\_GLOBAL)
lib = CDLL("/media/lzy/T7/darknet-master/darknet-master/libdarknet.so", RTLD_GLOBAL）#根据自己目录修改
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
lib.network_height.restype = c_int
 
predict = lib.network_predict
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)
 
set_gpu = lib.cuda_set_device
set_gpu.argtypes = [c_int]
 
make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE
 
get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int, POINTER(c_int)]
get_network_boxes.restype = POINTER(DETECTION)
 
make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)
 
free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]
 
free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]
 
network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]
 
reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]
 
load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
 
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
 
do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
 
free_image = lib.free_image
free_image.argtypes = [IMAGE]
 
letterbox_image = lib.letterbox_image
letterbox_image.argtypes = [IMAGE, c_int, c_int]
letterbox_image.restype = IMAGE
 
load_meta = lib.get_metadata
lib.get_metadata.argtypes = [c_char_p]
lib.get_metadata.restype = METADATA
 
load_image = lib.load_image_color
load_image.argtypes = [c_char_p, c_int, c_int]
load_image.restype = IMAGE


 
rgbgr_image = lib.rgbgr_image
rgbgr_image.argtypes = [IMAGE]
 
predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
 
def classify(net, meta, im):
    out = predict_image(net, im)
    res = []
    for i in range(meta.classes):
        res.append((meta.names[i], out[i]))
    res = sorted(res, key=lambda x: -x[1])
    return res
#检测 第三个参数image是照片的路径
def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
    im = load_image(image, 0, 0) #加载图片得到im对象
    num = c_int(0)
    pnum = pointer(num)
    predict_image(net, im)
    dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
    num = pnum[0]
    if (nms): do_nms_obj(dets, num, meta.classes, nms);
 
    res = []
    for j in range(num):
        for i in range(meta.classes):
            if dets[j].prob[i] > 0:
                b = dets[j].bbox
                res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
    res = sorted(res, key=lambda x: -x[1])
    free_image(im)
    free_detections(dets, num)
    return res


# 2018.04.25 用于绘制物体框
def showPicResult(image):
    img = cv2.imread(image)
    img3=img[...,::-1]
    cv2.imwrite(out_img, img3)
    for i in range(len(r)):
        x1=r[i][2][0]-r[i][2][2]/2
        y1=r[i][2][1]-r[i][2][3]/2
        x2=r[i][2][0]+r[i][2][2]/2
        y2=r[i][2][1]+r[i][2][3]/2
        im = cv2.imread(out_img)
        #draw different color rectangl
        
        #random color

        #r\_color = random.randint(0,255)#随机赋值
        #g = random.randint(0,255)
        #b = random.randint(0,255)
        #cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(r\_color,g,b),2)#画框
        
        if r[i][0] =="Car":
            cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(0,0,255),1)
            R=255
            g=50
            b=100
        if r[i][0] =="Pedistrian":
            cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(0,255,0),1)
            R=30
            g=255
            b=100
        if r[i][0] =="Cyclist":
            cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(255,0,0),1)
            R=50
            g=40
            b=255
        #cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(255,0,0),3)
        #putText 贴标
        x3 = int(x1+5)
        y3 = int(y1-10)
        x4 = int(x1)
        y4 = int()
        font = cv2.FONT_HERSHEY_SIMPLEX
        if ((x3<=im.shape[0]) and (y3>=0)):
            im2 = cv2.putText(im, str(r[i][0])+":"+str(round((r[i][1]\*100),2))+"%", (x3,y3), font, 0.2, (b,g,R) , 1)
        else:
            im2 = cv2.putText(im, str(r[i][0])+":"+str(round((r[i][1]\*100),2))+"%", (int(x1),int(y1+6)), font, 0.2, (b,g,R) , 1)
        #This is a method that works well. 
        #img2=im[...,::-1]
        cv2.imwrite(out_img, im)
    #img2=img[...,::-1]
    #cv2.imwrite(out\_img, img2)
    #img4 = cv2.imread(out\_img)
    #img5 = img4[...,::-1] 
    cv2.imshow('yolo\_image\_detector',cv2.imread(out_img))
    
if __name__ == "\_\_main\_\_":
    net = load_net(b"/media/lzy/T7/darknet-master/darknet-master/cfg/yolov3-kitti.cfg", b"/media/lzy/T7/darknet/backup/yolov3-kitti.backup", 0)#根据自己目录修改 配置表和训练好的权重文件
    meta = load_meta(b"/media/lzy/T7/darknet-master/darknet-master/kitti\_data/kitti.data")#根据自己目录修改 创建的kitti.data文件
    out_img = "/media/lzy/T7/darknet-master/darknet-master/kitti\_data/video/test\_result.jpg" #这个图片应该是为了视频读取图片尺寸等等需要的。可以通过抽帧然后保存到所需路径下,代码会在下面放出。
    video_tmp = "/media/lzy/T7/darknet-master/darknet-master/kitti\_data/video/video\_tmp.jpg"#加载路径，导入对象
    origin_video = '/home/lzy/Downloads/car\_detect.mp4'#读取本地视频
    
    # make a video\_object and init the video object
    cap = cv2.VideoCapture(origin_video)
    # define picture to\_down' coefficient of ratio
    scaling_factor = 0.5#0.5
    count = 0
    # img = cv2.imread(video\_tmp)

    p_num = 0
    size = (854,480)  #可以用cv2.imread(tmp\_video)这个图片
    fourcc = cv2.VideoWriter_fourcc(\*'XVID')#使用XVID编码器
    videoWrite = cv2.VideoWriter('/media/lzy/T7/darknet-master/darknet-master/kitti\_data/video/final\_out\_video.avi',fourcc,50,(427,240))# 根据图片的大小，创建写入对象 （文件名，支持的编码器，5帧，视频大小（图片大小））# loop until press 'esc' or 'q'
    while (cap.isOpened()):
        # collect current frame
        ret, frame = cap.read()
        if ret == True:
            count = count + 1
            #print count
        else:
            break
        #detect and show per 50 frames #照片抽帧成图片
        if count == 1:
            count = 0
            # resize the frame
            frame = cv2.resize(frame,None,fx=scaling_factor,fy=scaling_factor,interpolation=cv2.INTER_AREA)
            img_arr = Image.fromarray(frame)
            img_goal = img_arr.save(video_tmp)
            r = detect(net, meta,video_tmp)#检测，将结果赋值给r r是list类型
            
            #print r
        for j in range(len(r)):
            print("检测结果:",r[j][0], "概率",' : ', round((100\*r[j][1]),2),"%")
            print(r[j][2])
            print("")
            print('#\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*\*#')
            #display the rectangle of the objects in window
            showPicResult(video_tmp)
            p_num = p_num+1


![img](https://img-blog.csdnimg.cn/img_convert/82fe869941f793735b28205550a3c408.png)
![img](https://img-blog.csdnimg.cn/img_convert/ff44ec50aded3ee96909f0fd92f61078.png)

**既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上C C++开发知识点，真正体系化！**

**由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新**

**[如果你需要这些资料，可以戳这里获取](https://bbs.csdn.net/topics/618668825)**

W-1715663322699)]
[外链图片转存中...(img-A2QMCL65-1715663322699)]

**既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上C C++开发知识点，真正体系化！**

**由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新**

**[如果你需要这些资料，可以戳这里获取](https://bbs.csdn.net/topics/618668825)**