介绍
YOLO是基于深度学习端到端的实时目标检测系统，YOLO将目标区域预测和目标类别预测整合于单个神经网络模型中，实现在准确率较高的情况下快速目标检测与识别，更加适合现场应用环境。本案例，我们快速实现一个视频目标检测功能，实现的具体原理我们将在单独的文章中详细介绍。
下载编译
我们首先下载Darknet开发框架，Darknet开发框架是YOLO大神级作者自己用C语言编写的开发框架，支持GPU加速，有两种下载方式：
- 下载
git clone https://github.com/pjreddie/darknet
下载后，完整的文件内容，如下图所示：
编译：
cd darknet# 编译make
编译后的文件内容，如下图所示：
下载权重文件
我们这里下载的是“yolov3”版本，大小是200多M，“yolov3-tiny”比较小，30多M。
wget https://pjreddie.com/media/files/yolov3.weights
下载权重文件后，文件内容如下图所示：
上图中的“yolov3-tiny.weights”,"yolov2-tiny.weights"是我单独另下载的。
C语言预测
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
如图所示，我们已经预测出三种类别以及对应的概率值。模型输出的照片位于darknet根目录，名字是“predictions.jpg”，如下图所示：
让我们打开模型输出照片看下：
Python语言预测
我们首先需要将“darknet”文件夹内的“libdarknet.so”文件移动到“darknet/python”内，完成后如下图所示：
我们将使用Darknet内置的“darknet.py”,进行预测。预测之前，我们需要对文件进行修改：
- 默认py文件基于python2.0，所以对于python3.0及以上需要修改print
- 由于涉及到python和C之间的传值，所以字符串内容需要转码
- 使用绝对路径
修改完成后，如下图所示：
打开“darknet/cfg/coco.data”文件，将“names”也改为绝对路径（截图内没有修改，读者根据自己的实际路径修改）：
我们可以开始预测了，首先进入“darknet/python”然后执行“darknet.py”文件即可：
结果如下图所示：
对模型输出的结果做个简单的说明，如：
# 分别是：类别，识别概率，识别物体的X坐标，识别物体的Y坐标，识别物体的长度，识别物体的高度(b'dog', 0.999338686466217, (224.18377685546875, 378.4237060546875, 178.60214233398438, 328.1665954589844)
视频检测
from ctypes import *import randomimport cv2import numpy as npdef 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)-1def c_array(ctype, values): arr = (ctype*len(values))() arr[:] = values return arrclass 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("../python/libdarknet.so", RTLD_GLOBAL)lib.network_width.argtypes = [c_void_p]lib.network_width.restype = c_intlib.network_height.argtypes = [c_void_p]lib.network_height.restype = c_intpredict = lib.network_predictpredict.argtypes = [c_void_p, POINTER(c_float)]predict.restype = POINTER(c_float)set_gpu = lib.cuda_set_deviceset_gpu.argtypes = [c_int]make_image = lib.make_imagemake_image.argtypes = [c_int, c_int, c_int]make_image.restype = IMAGEget_network_boxes = lib.get_network_boxesget_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_boxesmake_network_boxes.argtypes = [c_void_p]make_network_boxes.restype = POINTER(DETECTION)free_detections = lib.free_detectionsfree_detections.argtypes = [POINTER(DETECTION), c_int]free_ptrs = lib.free_ptrsfree_ptrs.argtypes = [POINTER(c_void_p), c_int]network_predict = lib.network_predictnetwork_predict.argtypes = [c_void_p, POINTER(c_float)]reset_rnn = lib.reset_rnnreset_rnn.argtypes = [c_void_p]load_net = lib.load_networkload_net.argtypes = [c_char_p, c_char_p, c_int]load_net.restype = c_void_pdo_nms_obj = lib.do_nms_objdo_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]do_nms_sort = lib.do_nms_sortdo_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]free_image = lib.free_imagefree_image.argtypes = [IMAGE]letterbox_image = lib.letterbox_imageletterbox_image.argtypes = [IMAGE, c_int, c_int]letterbox_image.restype = IMAGEload_meta = lib.get_metadatalib.get_metadata.argtypes = [c_char_p]lib.get_metadata.restype = METADATAload_image = lib.load_image_colorload_image.argtypes = [c_char_p, c_int, c_int]load_image.restype = IMAGErgbgr_image = lib.rgbgr_imagergbgr_image.argtypes = [IMAGE]predict_image = lib.network_predict_imagepredict_image.argtypes = [c_void_p, IMAGE]predict_image.restype = POINTER(c_float)def convertBack(x, y, w, h): xmin = int(round(x - (w / 2))) xmax = int(round(x + (w / 2))) ymin = int(round(y - (h / 2))) ymax = int(round(y + (h / 2))) return xmin, ymin, xmax, ymaxdef array_to_image(arr): # need to return old values to avoid python freeing memory arr = arr.transpose(2,0,1) c, h, w = arr.shape[0:3] arr = np.ascontiguousarray(arr.flat, dtype=np.float32) / 255.0 data = arr.ctypes.data_as(POINTER(c_float)) im = IMAGE(w,h,c,data) return im, arrdef detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45): im, image = array_to_image(image) rgbgr_image(im) 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): a = dets[j].prob[0:meta.classes] if any(a): ai = np.array(a).nonzero()[0] for i in ai: 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]) if isinstance(image, bytes): free_image(im) free_detections(dets, num) return resif __name__ == "__main__": cap = cv2.VideoCapture(0) ret, img = cap.read() fps = cap.get(cv2.CAP_PROP_FPS) net = load_net(b"/Users/xiaomingtai/darknet/cfg/yolov2-tiny.cfg", b"/Users/xiaomingtai/darknet/yolov2-tiny.weights", 0) meta = load_meta(b"/Users/xiaomingtai/darknet/cfg/coco.data") cv2.namedWindow("img", cv2.WINDOW_NORMAL) while(True): ret, img = cap.read() if ret: r = detect(net, meta, img) for i in r: x, y, w, h = i[2][0], i[2][17], i[2][18], i[2][19] xmin, ymin, xmax, ymax = convertBack(float(x), float(y), float(w), float(h)) pt1 = (xmin, ymin) pt2 = (xmax, ymax) cv2.rectangle(img, pt1, pt2, (0, 255, 0), 2) cv2.putText(img, i[0].decode() + " [" + str(round(i[1] * 100, 2)) + "]", (pt1[0], pt1[1] + 20), cv2.FONT_HERSHEY_SIMPLEX, 1, [0, 255, 0], 4) cv2.imshow("img", img) if cv2.waitKey(1) & 0xFF == ord('q'): break 模型输出结果：
模型视频检测结果：
没有GPU的条件下还是不要选择yolov3了，很慢。
总结
本篇文章主要是YOLO快速上手，我们通过很少的代码就能实现不错的目标检测。当然，想熟练掌握YOLO，理解背后的原理是十分必要的，下篇文章将会重点介绍YOLO原理。