笔记补充：yolo识别、框选图片物体的python代码实现
前记：
（不知道怎么第一篇发出去的博客似乎一直搜不到，在此补充一封）
作用说明：学习笔记，主要用于自我记录。
（PS：本人菜鸟，文章仅供参考；如有错误，欢迎各位大神批评指正！）
最近刚刚接触yolo，由于yolo官网和网上各种资料几乎都是基于C语言的，本人觉得python比较简洁，故用python实现了C可实现的部分功能，包括（1）图片检测及画框、(2）本地视频检测、（3）webcam检测、（4）yolo结合ROS检测摄像头（webcam）视频。
该文此下只介绍（1）yolo在python下图片检测及画框。其余部分后续介绍。
【本系列文章代码全基于原作者代码，文中代码由于TAB缩进量可能会出现缩进问题】
1、使用环境和平台：
ubuntu 14.04+ python2.7+opencv2.4+yolo
关于yolo/darknet的安装：
git clone https://github.com/pjreddie/darknet
cd darknet
make有GPU的可自行安装CUDA（识别速度会快很多），修改相关参数。
yolo/darknet官网链接：
https://pjreddie.com/darknet/yolo/
2、检测图片的python代码
以下代码只是对源程序（darknet/python/darknet.py）的简单修改。
#!coding=utf-8
#modified by Leo at 2018.04.25
#function: 1,NOT overwrite the origin picture
# 2,print info BEFORE showing the display_window
from ctypes import *
import math
#import module named cv2 to draw
import cv2
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/username/darknet/libdarknet.so", RTLD_GLOBAL)
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
def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
im = load_image(image, 0, 0)
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
# display the pic after detecting. 2018.04.25
def showPicResult(image):
img = cv2.imread(image)
cv2.imwrite(out_img, img)
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)
cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(0,255,0),3)
#This is a method that works well.
cv2.imwrite(out_img, im)
cv2.imshow('yolo_image_detector', cv2.imread(out_img))
cv2.waitKey(0)
cv2.destroyAllWindows()
if __name__ == "__main__":
#notice the path of every file
net = load_net("/home/username/darknet/cfg/yolov3.cfg", "/home/username/darknet/weights/yolov3.weights", 0)
meta = load_meta("/home/username/darknet/cfg/coco.data")
origin_img = "/home/username/darknet/data/copy_dog.jpg"
out_img = "/home/username/darknet/data/test_result.jpg"
r = detect(net, meta, origin_img)
print r
#display the rectangle of the objects in window
showPicResult(origin_img)
yolo.weights文件如果没有的话请自行去yolo官网或Github上下载。
Notice：
1、注意cfg、weights等各个文件的路径，将程序中的各种文件路径全改为自己的（另外可能需要修改coco.data的内容，因为文件中涉及到coco.names的路径）；
2、此程序中对图片中识别到的物体画框的代码使用了opencv工具，没有安装的请自行安装（这里使用的是opencv2.4）;
3、注意cfg和weights文件的对应，如不对应可能导致识别图片不准确或错误。
3、代码解释
本程序主要增加部分：
import cv2
# display the pic after detecting.
def showPicResult(image):
img = cv2.imread(image)
cv2.imwrite(out_img, img)
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)
cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(0,255,0),3)
#This is a method that works well.
cv2.imwrite(out_img, im)
cv2.imshow('yolo_image_detector', cv2.imread(out_img))
cv2.waitKey(0)
cv2.destroyAllWindows()
for i in range(len(r)):r是一个list，其中存放了检测图片的信息，包括class（检测到的物体类别）、置信度、坐标，其中坐标包括x、y、w、h。
x、y：从左上角到物体中心点距离（float类型）；w、h：目标区域的宽和高（float类型）。
cv2.rectangle(im,(int(x1),int(y1)),(int(x2),int(y2)),(0,255,0),3)此函数实在目标区域绘制一个矩形，参数1：原图片，参数2：绘制矩形的左上角坐标，参数3: 右下角坐标，参数4: 矩形线条颜色，参数5: 线条粗细。（由于cv2中坐标为整数，所以程序中进行了类型转换float-->int）
对OpenCV不太了解的可以参考：
https://docs.opencv.org/3.0-beta/doc/py_tutorials/py_tutorials.html
后记：
程序改动不大，理解起来很简单，在我电脑上是完全可以实现的，如有问题欢迎批评指正！
联系邮箱：[email protected]
（PS：后续部分，陆续奉上。）