Tensorflow+SSD+Yolo（目标检测）文章12：YOLO_v3视频的读取和qtpy的操作

12.YOLO_v3视频的读取和qtpy的操作
（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/11224807
或者在下载区搜索名字：12.YOLO_v3视频的读取和qtpy的操作.zip–深度学习文章12）

---

正文

---

一、分点总结
https://blog.csdn.net/a88770202/article/details/87108823 视频的读取！！！

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()

https://blog.csdn.net/Lay_ZRS/article/details/88549644

https://blog.csdn.net/DumpDoctorWang/article/details/80515861

汇总：

# -*- coding: utf-8 -*-
"""
Class definition of YOLO_v3 style detection model on image and video
"""

import colorsys
import os
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 detect_image(self, image):
        start = timer()

        if self.model_image_size != (None, None):
            assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
            assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
            boxed_image = letterbox_image(image, tuple(reversed(self.model_image_size)))
        else:
            new_image_size = (image.width - (image.width % 32),
                              image.height - (image.height % 32))
            boxed_image = letterbox_image(image, new_image_size)
        image_data = np.array(boxed_image, dtype='float32')

        print(image_data.shape)
        image_data /= 255.
        image_data = np.expand_dims(image_data, 0)  # Add batch dimension.

        out_boxes, out_scores, out_classes = self.sess.run(
            [self.boxes, self.scores, self.classes],
            feed_dict={
                self.yolo_model.input: image_data,
                self.input_image_shape: [image.size[1], image.size[0]],
                K.learning_phase(): 0
            })

        print('Found {} boxes for {}'.format(len(out_boxes), 'img'))

        font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
                    size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
        thickness = (image.size[0] + image.size[1]) // 300

        for i, c in reversed(list(enumerate(out_classes))):
            predicted_class = self.class_names[c]
            box = out_boxes[i]
            score = out_scores[i]

            top, left, bottom, right = box
            top = max(0, np.floor(top + 0.5).astype('int32'))
            left = max(0, np.floor(left + 0.5).astype('int32'))
            bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
            right = min(image.size[0], np.floor(right + 0.5).astype('int32'))

            label = '{} {:.2f} '.format(predicted_class, score) + '({} {}) '.format(np.floor((top+bottom)/2+0.5).astype('int32'), np.floor((left+right)/2+0.5).astype('int32'))
            draw = ImageDraw.Draw(image)
            label_size = draw.textsize(label, font)
            print(label, (left, top), (right, bottom))

            if top - label_size[1] >= 0:
                text_origin = np.array([left, top - label_size[1]])
            else:
                text_origin = np.array([left, top + 1])

            # My kingdom for a good redistributable image drawing library.
            for i in range(thickness):
                draw.rectangle(
                    [left + i, top + i, right - i, bottom - i],
                    outline=self.colors[c])
            draw.rectangle(
                [tuple(text_origin), tuple(text_origin + label_size)],
                fill=self.colors[c])
            draw.text(text_origin, label, fill=(0, 0, 0), font=font)
            del draw

        end = timer()
        print(end - start)
        return image

    def close_session(self):
        self.sess.close()

# def detect_video(yolo, video, output_path=""):
#     import cv2
#     video_path = os.path.join(video)
#
#     if (os.path.exists(video_path) and video != ''):
#         vid = cv2.VideoCapture(video_path)
#     else:
#         vid = cv2.VideoCapture(0)
#         video = 'your_camera.mp4'
#
#     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(frame)
#         image = yolo.detect_image(image)
#         result = np.asarray(image)
#         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()

#  添加的


def detect_video(yolo, video, output_path=""):
    import cv2

    video_path = os.path.join(video)

    if (os.path.exists(video_path) and video != ''):
        vid = cv2.VideoCapture(video_path)
    else:
        vid = cv2.VideoCapture(0)
        video = 'your_camera.mp4'


    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()
        if frame is None:
            break
        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()




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__':

    # # 检测单张图片
    # detect_img(YOLO(), img_path='.\photo/00002.jpg')  # 检测输入图片的路径

    # 检测视频
    video = '.\photo/ee.mp4'
    detect_video(YOLO(), video, output_path="ee_result4.mp4")

    # # 检测摄像头
    # video = ''
    # detect_video(YOLO(), video, output_path="")


    # i = 0
    # # 检测单张图片
    # 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')  # 检测输入图片的路径
    #





# if __name__ == '__main__':
#     # file = 'model_data/coco_classes.txt'
#     # # detect images in test floder.
#     # # 下面是测试图片用的
#     # for (root, dirs, files) in os.walk('./test'):
#     #    if files:
#     #        for f in files:
#     #            print(f)
#     #            path = os.path.join(root, f)
#     #            image = Image.open(path)
#     #            image = detect_img(YOLO(), path)
#     #            cv2.imwrite('pic/' + f, image)


    # # Test on some demo image and visualize output.
    # path = './test/'
    # image_names = sorted(os.listdir(path))         # 获取测试文件夹所有图片
    # i = 0
    # for it  in image_names:
    #
    #     image = Image.open(image_names)
    #     i+=1
    #     if i>15: break                               # 测试9张图片，数字9可以改变
    #     image = detect_img(YOLO(), image_names)