我使用的是AB大神的darknet版yolov3，这里默认环境已经配置好了
当yoloGui文件写好之后发现yolov3自带的darknet_images.py文件中的检测函数一直报错，后来寻找到一位大佬的修改过的可以进行批量检测的代码，略加修改发现可用，在使用时需要将yolov3的相关文件改为自己的路径
在darknet文件夹下新建detect.py文件，复制以下内容
import argparse
import os
import glob
import random
import darknet
import time
import cv2
import numpy as np
def parser():
parser = argparse.ArgumentParser(description="YOLO Object Detection")
parser.add_argument("--input", type=str, default="",
help="image source. It can be a single image, a"
"txt with paths to them, or a folder. Image valid"
" formats are jpg, jpeg or png."
"If no input is given, ")
parser.add_argument("--batch_size", default=1, type=int,
help="number of images to be processed at the same time")
parser.add_argument("--weights", default="myData/backup/my_yolov3_last.weights",#改为自己的路径
help="yolo weights path")
parser.add_argument("--dont_show", action='store_true',
help="windown inference display. For headless systems")
parser.add_argument("--ext_output", action='store_true',
help="display bbox coordinates of detected objects")
parser.add_argument("--save_labels", action='store_true',
help="save detections bbox for each image in yolo format")
parser.add_argument("--config_file", default="./cfg/my_yolov3.cfg",
help="path to config file")
parser.add_argument("--data_file", default="./cfg/my_data.data",
help="path to data file")
parser.add_argument("--thresh", type=float, default=.25,
help="remove detections with lower confidence")
return parser.parse_args()
def check_arguments_errors(args):
assert 0 < args.thresh < 1, "Threshold should be a float between zero and one (non-inclusive)"
if not os.path.exists(args.config_file):
raise(ValueError("Invalid config path {}".format(os.path.abspath(args.config_file))))
if not os.path.exists(args.weights):
raise(ValueError("Invalid weight path {}".format(os.path.abspath(args.weights))))
if not os.path.exists(args.data_file):
raise(ValueError("Invalid data file path {}".format(os.path.abspath(args.data_file))))
if args.input and not os.path.exists(args.input):
raise(ValueError("Invalid image path {}".format(os.path.abspath(args.input))))
def check_batch_shape(images, batch_size):
"""
Image sizes should be the same width and height
"""
shapes = [image.shape for image in images]
if len(set(shapes)) > 1:
raise ValueError("Images don't have same shape")
if len(shapes) > batch_size:
raise ValueError("Batch size higher than number of images")
return shapes[0]
def load_images(images_path):
"""
If image path is given, return it directly
For txt file, read it and return each line as image path
In other case, it's a folder, return a list with names of each
jpg, jpeg and png file
"""
input_path_extension = images_path.split('.')[-1]
if input_path_extension in ['jpg', 'jpeg', 'png']:
return [images_path]
elif input_path_extension == "txt":
with open(images_path, "r") as f:
return f.read().splitlines()
else:
return glob.glob(
os.path.join(images_path, "*.jpg")) + \
glob.glob(os.path.join(images_path, "*.png")) + \
glob.glob(os.path.join(images_path, "*.jpeg"))
def prepare_batch(images, network, channels=3):
width = darknet.network_width(network)
height = darknet.network_height(network)
darknet_images = []
for image in images:
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image_resized = cv2.resize(image_rgb, (width, height),
interpolation=cv2.INTER_LINEAR)
custom_image = image_resized.transpose(2, 0, 1)
darknet_images.append(custom_image)
batch_array = np.concatenate(darknet_images, axis=0)
batch_array = np.ascontiguousarray(batch_array.flat, dtype=np.float32)/255.0
darknet_images = batch_array.ctypes.data_as(darknet.POINTER(darknet.c_float))
return darknet.IMAGE(width, height, channels, darknet_images)
def image_detection(image_path,network, class_names, class_colors, thresh):
# Darknet doesn't accept numpy images.
# Create one with image we reuse for each detect
width = darknet.network_width(network)
height = darknet.network_height(network)
darknet_image = darknet.make_image(width, height, 3)
image = cv2.imread(image_path)
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image_resized = cv2.resize(image_rgb, (width, height),
interpolation=cv2.INTER_LINEAR)
darknet.copy_image_from_bytes(darknet_image, image_resized.tobytes())
detections = darknet.detect_image(network, class_names, darknet_image, thresh=thresh)
darknet.free_image(darknet_image)
image = darknet.draw_boxes(detections, image_resized, class_colors)
#return cv2.cvtColor(image, cv2.COLOR_BGR2RGB), detections#当需要批量测试时使用这一行
return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)#当使用yoloGui时使用这一行
def batch_detection(network, images, class_names, class_colors,
thresh=0.25, hier_thresh=.5, nms=.45, batch_size=4):
image_height, image_width, _ = check_batch_shape(images, batch_size)
darknet_images = prepare_batch(images, network)
batch_detections = darknet.network_predict_batch(network, darknet_images, batch_size, image_width,
image_height, thresh, hier_thresh, None, 0, 0)
batch_predictions = []
for idx in range(batch_size):
num = batch_detections[idx].num
detections = batch_detections[idx].dets
if nms:
darknet.do_nms_obj(detections, num, len(class_names), nms)
predictions = darknet.remove_negatives(detections, class_names, num)
images[idx] = darknet.draw_boxes(predictions, images[idx], class_colors)
batch_predictions.append(predictions)
darknet.free_batch_detections(batch_detections, batch_size)
return images, batch_predictions
def image_classification(image, network, class_names):
width = darknet.network_width(network)
height = darknet.network_height(network)
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image_resized = cv2.resize(image_rgb, (width, height),
interpolation=cv2.INTER_LINEAR)
darknet_image = darknet.make_image(width, height, 3)
darknet.copy_image_from_bytes(darknet_image, image_resized.tobytes())
detections = darknet.predict_image(network, darknet_image)
predictions = [(name, detections[idx]) for idx, name in enumerate(class_names)]
darknet.free_image(darknet_image)
return sorted(predictions, key=lambda x: -x[1])
def convert2relative(image, bbox):
"""
YOLO format use relative coordinates for annotation
"""
x, y, w, h = bbox
height, width, _ = image.shape
return x/width, y/height, w/width, h/height
def save_annotations(name, image, detections, class_names):
"""
Files saved with image_name.txt and relative coordinates
"""
file_name = name.split(".")[:-1][0] + ".txt"
with open(file_name, "w") as f:
for label, confidence, bbox in detections:
x, y, w, h = convert2relative(image, bbox)
label = class_names.index(label)
f.write("{} {:.4f} {:.4f} {:.4f} {:.4f}\n".format(label, x, y, w, h))
def batch_detection_example():
args = parser()
check_arguments_errors(args)
batch_size = 3
random.seed(3) # deterministic bbox colors
network, class_names, class_colors = darknet.load_network(
args.config_file,
args.data_file,
args.weights,
batch_size=batch_size
)
image_names = ['data/horses.jpg', 'data/horses.jpg', 'data/eagle.jpg']
images = [cv2.imread(image) for image in image_names]
images, detections, = batch_detection(network, images, class_names,
class_colors, batch_size=batch_size)
for name, image in zip(image_names, images):
cv2.imwrite(name.replace("data/", ""), image)
print(detections)
def get_files(dir, suffix):
res = []
for root, directory, files in os.walk(dir):
for filename in files:
name, suf = os.path.splitext(filename)
if suf == suffix:
#res.append(filename)
res.append(os.path.join(root, filename))
return res
def bbox2points_zs(bbox):
"""
From bounding box yolo format
to corner points cv2 rectangle
"""
x, y, w, h = bbox
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, ymax
def main():
args = parser()
check_arguments_errors(args)
input_dir = '/home/your/darknet'
config_file = '/home/your/darknet/cfg/my_yolov3.cfg'
data_file = '/home/your/darknet/cfg/my_data.data'
weights = '/home/your/darknet/myData/backup/my_yolov3_last.weights'#改为自己的路径
random.seed(3) # deterministic bbox colors
network, class_names, class_colors = darknet.load_network(
config_file,
data_file,
weights,
batch_size=args.batch_size
)
src_width = darknet.network_width(network)
src_height = darknet.network_height(network)
#生成保存图片路径文件夹
save_dir = os.path.join(input_dir, 'object_result')
# 去除首位空格
save_dir=save_dir.strip()
# 去除尾部 \ 符号
save_dir=save_dir.rstrip("\\")
# 判断路径是否存在 # 存在 True # 不存在 False
isExists=os.path.exists(save_dir)
# 判断结果
if not isExists:
# 如果不存在则创建目录 # 创建目录操作函数
os.makedirs(save_dir)
print(save_dir+' 创建成功')
else:
# 如果目录存在 则不创建，并提示目录已存在
print(save_dir + ' 目录已存在')
image_list = get_files(input_dir, '.jpg')
total_len = len(image_list)
index = 0
#while True:
for i in range(0, total_len):
image_name = image_list[i]
src_image = cv2.imread(image_name)
cv2.imshow('src_image', src_image)
cv2.waitKey(1)
prev_time = time.time()
image, detections = image_detection(
image_name, network, class_names, class_colors, args.thresh)
#'''
file_name, type_name = os.path.splitext(image_name)
#print(file_name)
#print(file_name.split(r'/'))
print(''.join(file_name.split(r'/')[-1]) + 'bbbbbbbbb')
cut_image_name_list = file_name.split(r'/')[-1:] #cut_image_name_list is list
save_dir_image = os.path.join(save_dir ,cut_image_name_list[0])
if not os.path.exists(save_dir_image):
os.makedirs(save_dir_image)
cut_image_name = ''.join(cut_image_name_list) #list to str
object_count = 0
for label, confidence, bbox in detections:
cut_image_name_temp = cut_image_name + "_{}.jpg".format(object_count)
object_count += 1
xmin, ymin, xmax, ymax = bbox2points_zs(bbox)
print("aaaaaaaaa x,{} y,{} w,{} h{}".format(xmin, ymin, xmax, ymax))
xmin_coordinary = (int)(xmin * src_image.shape[1] / src_width-0.5)
ymin_coordinary = (int)(ymin * src_image.shape[0] / src_height-0.5)
xmax_coordinary = (int)(xmax * src_image.shape[1] / src_width+0.5)
ymax_coordinary = (int)(ymax * src_image.shape[0] / src_height+0.5)
if xmin_coordinary>src_image.shape[1]:
xmin_coordinary = src_image.shape[1]
if ymin_coordinary>src_image.shape[0]:
ymin_coordinary = src_image.shape[0]
if xmax_coordinary>src_image.shape[1]:
xmax_coordinary = src_image.shape[1]
if ymax_coordinary>src_image.shape[0]:
ymax_coordinary = src_image.shape[0]
if xmin_coordinary < 0:
xmin_coordinary = 0
if ymin_coordinary < 0:
ymin_coordinary = 0
if xmax_coordinary < 0:
xmax_coordinary = 0
if ymax_coordinary < 0:
ymax_coordinary = 0
print("qqqqqqqq x,{} y,{} w,{} h{}".format(xmin_coordinary, ymin_coordinary, xmax_coordinary, ymax_coordinary))
out_iou_img = np.full((ymax_coordinary - ymin_coordinary, xmax_coordinary - xmin_coordinary, src_image.shape[2]), 114, dtype=np.uint8)
out_iou_img[:,:] = src_image[ymin_coordinary:ymax_coordinary,xmin_coordinary:xmax_coordinary]
cv2.imwrite(os.path.join(save_dir_image,cut_image_name_temp),out_iou_img)
#'''
#if args.save_labels:
#if True:
#save_annotations(image_name, image, detections, class_names)
darknet.print_detections(detections, args.ext_output)
fps = int(1/(time.time() - prev_time))
print("FPS: {}".format(fps))
if not args.dont_show:
#cv2.imshow('Inference', image)
cv2.waitKey(1)
#if cv2.waitKey() & 0xFF == ord('q'):
#break
index += 1
if __name__ == "__main__":
# unconmment next line for an example of batch processing
# batch_detection_example()
main()
接下来是yoloGui.py文件，此文件也是参考一位大佬的，然后略加修改，具体博客找不到了，在此感谢这位大佬，在运行前须自行在当前目录下创建img文件夹，并将需要检测的图片放入img文件夹，同时在img文件夹中创建result文件夹，用于保存检测结果。此文件只支持图片的检测，如果需要视频流检测，可以自行修改。 在运行过程中我发现一次只能运行4-5此就会爆现存，应该可以静态全局加载权重文件解决，欢迎各位指正。
应注意各个路径都正确，包括cfg文件等
在darknet文件夹下新建yoloGui.py文件，复制以下内容
import cv2
import numpy as np
from PyQt5.QtWidgets import *
from PyQt5.QtGui import QIcon, QPixmap, QImage
import os
import sys
import detect
from PIL import Image
import darknet
import random
import string
crop = False
count = False
class MyClassImage(QWidget):
def __init__(self):
super().__init__()
self.label2 = None
self.label3 = None
self.initUI() # 初始化界面并并展示
self.openfile_name_image = '' # 选择文件的路径
self.image = None
# 定义初始化组件
def initUI(self):
# 设置窗口大小
self.resize(850, 400)
# 设置窗口名称
self.setWindowTitle("检测图片")
# 创建按钮
btn5 = QPushButton("退出检测图片", self)
btn5.clicked.connect(self.close)
btn1 = QPushButton("选择检测图片", self)
# 关键点击事件，点击止呕启动self.select_image函数
btn1.clicked.connect(self.select_image)
btn2 = QPushButton("开始检测", self)
# 关键点击事件，点击止呕启动self.detect函数
btn2.clicked.connect(self.detect)
# 创建标签，可以放文本或图片或空
self.label2 = QLabel("", self)
self.label2.resize(400, 300)
self.label3 = QLabel("", self)
self.label3.resize(400, 300)
label4 = QLabel(" 原始图片", self)
label5 = QLabel(" 检测图片", self)
# 定义网格布局
grid1 = QGridLayout()
grid1.addWidget(label4, 0, 0)
# 网格布局 第一行第二列防止label5
grid1.addWidget(label5, 0, 1)
hlo = QHBoxLayout()
hlo.addStretch()
grid = QGridLayout()
# vlo.addStretch(0)
grid.addWidget(btn1, 0, 0)
grid.addWidget(btn2, 0, 1)
grid.addWidget(btn5, 0, 2)
hlo1 = QHBoxLayout()
hlo1.addWidget(self.label2)
hlo1.addWidget(self.label3)
vlo = QVBoxLayout(self)
vlo.addLayout(grid)
vlo.addLayout(hlo1)
vlo.addStretch(1)
vlo.addLayout(grid1)
vlo.addStretch(0)
self.show()
def closeEvent(self, event):
result = QMessageBox.question(self, "提示：", "您真的要退出程序吗",
QMessageBox.Yes | QMessageBox.No, QMessageBox.Yes)
if result == QMessageBox.Yes:
event.accept()
else:
event.ignore()
def detect(self):
if self.image is None:
print('没有选择图片')
elif self.image is not None:
# 检测图片
run_detect(self.openfile_name_image)
# 读取检测之后的图片
img = cv2.imread('img/result/'+self.openfile_name_image.split('/')[-1])
img = cv2.resize(img, (400, 300), interpolation=cv2.INTER_AREA)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# cv2.imshow('test', img)
# cv2.waitKey(20)
# 将图片放在标签self.label3中
a = QImage(img.data, img.shape[1], img.shape[0], img.shape[1] * 3, QImage.Format_RGB888)
self.label3.setPixmap(QPixmap.fromImage(a))
pass
def select_image(self):
# temp为选择文件的路径 这里打开的是这个main.py函数的同级目录下的img文件夹
temp, _ = QFileDialog.getOpenFileName(self, "选择照片文件", r"./img/")
if temp is not None:
self.openfile_name_image = temp
# 读取选择的图片
self.image = cv2.imread(self.openfile_name_image)
# print(self.openfile_name_image)
# 将路径中的图片读取之后放在self.label2
self.label2.setPixmap(QPixmap(str(self.openfile_name_image)))
self.label2.setScaledContents(True)
# 读取收缩放至(400, 300)
self.label2.setMaximumSize(400, 300)
self.label2.setScaledContents(True)
# 重写这个函数
def run_detect(path):
try:
image = Image.open(path)
except:
print('Open Error! Try again!')
else:
##这里是模型检测函数，替换成自己的即可，这个函数返回的就是检测好的图片，然后保存在本地的同级目录下的img/result
args = detect.parser()
detect.check_arguments_errors(args)
random.seed(3) # deterministic bbox colors
network, class_names, class_colors = darknet.load_network(
args.config_file,
args.data_file,
args.weights,
batch_size=args.batch_size
)
img_path = path
r_image = detect.image_detection(img_path,network, class_names, class_colors, args.thresh)
#r_image.save('img/result/' + path.split('/')[-1])#这里我报了没有save这个模块的错，遂改为imwrite
cv2.imwrite('img/result/' + path.split('/')[-1],r_image)
if __name__ == '__main__':
app = QApplication(sys.argv)
mc = MyClassImage()
sys.exit(app.exec_())
以下是运行截图：
这只是个简易的界面编程，我也处于初学阶段，后续如果有更好的idea也会和大家分享，有不对的或不完善的地方也欢迎大家批评指正。后续会对界面进行一些美化，然后新增一些功能，会想办法解决out of memory的问题
对界面进行美化，新增输出物品label和number功能yolov3的Gui界面（2）--美化页面+输出识别物体名称及数量_perfectdisaster的博客-CSDN博客
解决out of memory问题，新增摄像头检测功能
扫一扫
265
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
