Darknet-yolo3调用python接口批量检测图片

根目录下找到darknet.py 文件，在pycharm中运行报错

OSError: libdarknet.so: cannot open shared object file: No such file or directory

原因是darknet.py需要依赖 libdarknet.so文件，该文件其实就在安装好的darknet目录下，把libdarknet.so和darknet.py放在同一目录下就行了。(将libdarknet.so复制到了darknet.py目录下还是报错，这是因为libdarknet.so本身依赖其所在目录的其他库，应该将darknet.py复制到libdarknet.so所在目录)
并将darknet.py中的

#lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
lib = CDLL("libdarknet.so", RTLD_GLOBAL)

修改为

#lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
# 使用libdarknet.so的绝对路径替换
lib = CDLL("/home/alex/darknet-master/libdarknet.so", RTLD_GLOBAL)
# lib = CDLL("libdarknet.so", RTLD_GLOBAL)

再次运行报错

ctypes.ArgumentError: argument 1: <class 'TypeError'>: wrong type

原因是net = load_net(“cfg/tiny-yolo.cfg”, “tiny-yolo.weights”, 0)这个函数最后会将"cfg/tiny-yolo.cfg", "tiny-yolo.weights"这些参数传给刚才说到的libdarknet.so这个库中，而这个库是用c/c++来写的，所以出现了这个错误。解决方法是在出错的字符串前面添加一个b就行了，如：

net = load_net(b"cfg/yolov3.cfg", b"yolov3.weights", 0)
meta = load_meta("cfg/coco.data")
r = detect(net, meta, b"data/dog.jpg")

终端中再次运行

python darknet.py

结果如下

然后就能添加自己的代码了。下面正式调用Python借口检测图片，代码是从该博客搬运来的

# coding: utf-8
from ctypes import *
import math
import random
import os
import time
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/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
lib = CDLL("/home/alex/darknet-master/libdarknet.so", RTLD_GLOBAL)
# lib = CDLL("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

if __name__ == "__main__":
# 设置当前使用的GPU设备仅为0号设备  设备名称为'/gpu:0'
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
net = load_net(b"cfg/yolov3.cfg", b"yolov3.weights", 0)
meta = load_meta(b"cfg/coco.data")
# 测试数据集的路径
test_dir = '/home/alex/Desktop/deeplearning/python_exercise/pics'
# 检测结果保存路径
save_dir = '/home/alex/darknet-master/data/out/'
if not os.path.exists(save_dir):
os.mkdir(save_dir)

pics = os.listdir(test_dir)
count = 0
for im in pics:
img = os.path.join(test_dir, im)
s = time.time()
r = detect(net, meta, img.encode('utf-8'))
# 输出的检测结果中坐标信息为目标的中心点坐标和box的w和h
print("一张图检测耗时：%.3f秒" % (time.time() - s))
im = cv2.imread(img)
for res in r:
x1 = int(res[2][0] - (res[2][2] / 2))
y1 = int(res[2][1] - (res[2][3] / 2))
x2 = x1 + int(res[2][2])
y2 = y1 + int(res[2][3])
cv2.rectangle(im, (x1 - 5, y1 - 5), (x2 + 5, y2 + 5), (0, 255, 0), 2)
cv2.putText(im, str(res[0]).split("'")[1], (x1 - 10, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
cv2.imwrite(save_dir + str(count) + '.jpg', im)
count += 1

在终端运行该文件即可

python darknet.py

该博客仅作学习记录，每天进步一点点

参考文献：
darknet的Python借口使用1
Darknet YoloV3调用python接口进行批量图片检测

• 点赞
• 收藏
• 分享
• 文章举报