10.YOLO_v3实现视频化以及界面化和打包操作
(写在每篇深度学习文章系列的前面,该系列的文章是我2019年做毕设时的步骤总结,是能实现的,不和其他很多博客一样瞎糊弄人浪费时间。写下这些文章一方面为了方便后来者,一方面也为了自己以后的步骤复现等。
另外,如果我给的那些参考帖子看不了了,可以到我的博客下载区那里去下载对应的压缩文件,我把里面所有的链接网页都截了长图,所以不用担心我给的参考帖子链接失效。
其次,如果我给的参考链接侵犯了该链接博主的权益,烦请告知,必当第一时间删掉。由于本人参考帖子较多,如果侵犯了请原谅,我会删掉。也谢谢各位在路上帮助过我的,谢谢了。
还有就是,如果积分太高了,请告诉我怎么把积分降低,我也不太清楚怎么弄,积分会随着下载次数增加逐渐增加。你知道的话怎么降的话可以留言给我。
emm, 最后的最后,如果你觉得这篇博文有用,请点个赞哩,感谢!~~)
(博客下载区:https://download.csdn.net/download/lininggggggg/11224800
或者在下载区搜索名字:10.YOLO_v3实现视频化以及界面化和打包操作.zip–深度学习文章10)
正文
https://blog.csdn.net/a88770202/article/details/87108823 视频的读取!!!
https://blog.csdn.net/Lay_ZRS/article/details/88549644
https://blog.csdn.net/DumpDoctorWang/article/details/80515861
一、视频的读取
如果按照之前给的yolo.py文件里的视频软件进行测试的话会发现总是测试识别不出来,这个其实有个大坑来着。
首先,都测不到,要么标记框瞎框,有的边界都溢出int了(一度怀疑人生),后来看了一篇博文说可能是opencv的图片读取BGR顺序和Image图片的RGB读取顺序不同,然后看了一下detect_video函数发现拿图片帧去处理的是Image而用cv2.show的还是Image顺序,确实没转换过去,于是百度了一波转换方法,改了改代码就可以正常识别了。修改后代码如下:即把这段代码放到yolo.py文件里的那个同样的函数的地方,之前那个删掉即可。
def detect_video(yolo, video_path, output_path=""):
import cv2
vid = cv2.VideoCapture(video_path)
if not vid.isOpened():
raise IOError("Couldn't open webcam or video")
video_FourCC = int(vid.get(cv2.CAP_PROP_FOURCC))
video_fps = vid.get(cv2.CAP_PROP_FPS)
video_size = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))
isOutput = True if output_path != "" else False
if isOutput:
print("!!! TYPE:", type(output_path), type(video_FourCC), type(video_fps), type(video_size))
out = cv2.VideoWriter(output_path, video_FourCC, video_fps, video_size)
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))#Opencv转PIL
image = yolo.detect_image(image)
result = cv2.cvtColor(np.asarray(image), cv2.COLOR_RGB2BGR)#显示的时候再PIL转回Opencv
#
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
#
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", result)
# if isOutput:
# out.write(result)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
yolo.close_session()
然后在该文件的末尾加上下面的代码即可运行:
加法1:(没实践过)
def detect_img(yolo):
while True:
img = input('Input image filename:')
try:
image = Image.open(img)
except:
print('Open Error! Try again!')
continue
else:
r_image = yolo.detect_image(image)
r_image.show()
yolo.close_session()
if __name__ == '__main__':
if (int(input("Please input detect_type 1->image, 2->video\n")) == 1):
detect_img(YOLO())
else:
detect_video(YOLO(), input("Input video filename:\n"))
加法2:
def detect_img(yolo, img_path='test.png'):
image = Image.open(img_path)
import time
t1 = time.time()
####
outdir="E:\GraduationProject\Data\keras-yolo3-master5\photo/store"
r_image = yolo.detect_image(image)
r_image.save(os.path.join(outdir, os.path.basename(img_path)))
####
print('time: {}'.format(time.time() - t1))
r_image.show()
# yolo.close_session()
if __name__ == '__main__':
# 1.15, 0.24
yolo = YOLO()
#
video = '.\photo/ee.mp4'
detect_video(yolo, video, output_path="ee_result5.mp4")
# #
# video = ''
# detect_video(yolo, video, output_path="ee_result8.mp4")
最后的yolo.py的最终代码如下:
# """
# Class definition of YOLO_v3 style detection model on image and video
# """
# # 我记得应该是运行yolo1才能正常运行全部功能
# import colorsys
# from timeit import default_timer as timer
#
# import numpy as np
# from keras import backend as K
# from keras.models import load_model
# from keras.layers import Input
# from PIL import Image, ImageFont, ImageDraw
#
# from yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
# from yolo3.utils import letterbox_image
# import os
# from keras.utils import multi_gpu_model
#
# class YOLO(object):
# _defaults = {
# "model_path": 'model_data/yolo.h5',
# "anchors_path": 'model_data/yolo_anchors.txt',
# "classes_path": 'model_data/coco_classes.txt',
# "score" : 0.3,
# "iou" : 0.45,
# "model_image_size" : (416, 416),
# "gpu_num" : 1,
# }
#
# @classmethod
# def get_defaults(cls, n):
# if n in cls._defaults:
# return cls._defaults[n]
# else:
# return "Unrecognized attribute name '" + n + "'"
#
# def __init__(self, **kwargs):
# self.__dict__.update(self._defaults) # set up default values
# self.__dict__.update(kwargs) # and update with user overrides
# self.class_names = self._get_class()
# self.anchors = self._get_anchors()
# self.sess = K.get_session()
# self.boxes, self.scores, self.classes = self.generate()
#
# def _get_class(self):
# classes_path = os.path.expanduser(self.classes_path)
# with open(classes_path) as f:
# class_names = f.readlines()
# class_names = [c.strip() for c in class_names]
# return class_names
#
# def _get_anchors(self):
# anchors_path = os.path.expanduser(self.anchors_path)
# with open(anchors_path) as f:
# anchors = f.readline()
# anchors = [float(x) for x in anchors.split(',')]
# return np.array(anchors).reshape(-1, 2)
#
# def generate(self):
# model_path = os.path.expanduser(self.model_path)
# assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
#
# # Load model, or construct model and load weights.
# num_anchors = len(self.anchors)
# num_classes = len(self.class_names)
# is_tiny_version = num_anchors==6 # default setting
# try:
# self.yolo_model = load_model(model_path, compile=False)
# except:
# self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \
# if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
# self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
# else:
# assert self.yolo_model.layers[-1].output_shape[-1] == \
# num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
# 'Mismatch between model and given anchor and class sizes'
#
# print('{} model, anchors, and classes loaded.'.format(model_path))
#
# # Generate colors for drawing bounding boxes.
# hsv_tuples = [(x / len(self.class_names), 1., 1.)
# for x in range(len(self.class_names))]
# self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
# self.colors = list(
# map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
# self.colors))
# np.random.seed(10101) # Fixed seed for consistent colors across runs.
# np.random.shuffle(self.colors) # Shuffle colors to decorrelate adjacent classes.
# np.random.seed(None) # Reset seed to default.
#
# # Generate output tensor targets for filtered bounding boxes.
# self.input_image_shape = K.placeholder(shape=(2, ))
# if self.gpu_num>=2:
# self.yolo_model = multi_gpu_model(self.yolo_model, gpus=self.gpu_num)
# boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
# len(self.class_names), self.input_image_shape,
# score_threshold=self.score, iou_threshold=self.iou)
# return boxes, scores, classes
#
# def close_session(self):
# self.sess.close()
#
#
# if __name__ == '__main__':
#
# # #
# # detect_img(YOLO(), img_path='.\photo/00002.jpg')
#
# #
# video = '.\photo/ee.mp4'
# detect_video(YOLO(), video, output_path="ee_result5.mp4")
#
# # #
# # video = ''
# # detect_video(YOLO(), video, output_path="")
#
#
# # i = 0
# # #
# # path = 'E:\GraduationProject\Data\keras-yolo3-master5\pic/'
# # if i<=11:
# # i += 1
# # image_names = os.path.join(path, i, '.jpg')
# # detect_img(YOLO(), img_path='image_names') #
# #
#
#
"""
Class definition of YOLO_v3 style detection model on image and video
"""
# 我记得应该是运行yolo1才能正常运行全部功能
import colorsys
from timeit import default_timer as timer
import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw
from yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
from yolo3.utils import letterbox_image
import os
from keras.utils import multi_gpu_model
class YOLO(object):
_defaults = {
"model_path": 'model_data/yolo.h5',
"anchors_path": 'model_data/yolo_anchors.txt',
"classes_path": 'model_data/coco_classes.txt',
"score" : 0.3,
"iou" : 0.45,
"model_image_size" : (416, 416),
"gpu_num" : 1,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute n