Обнаружение объекта Тензор потока прерывает видео петлю нажатием кнопки в PyQT - PullRequest
Новая
       6

Обнаружение объекта Тензор потока прерывает видео петлю нажатием кнопки в PyQT

0 голосов
/ 26 сентября 2019

Привет. Я работаю над проектом по обнаружению табличек автомобилей и их распознаванию, и у меня все получилось, но я сталкиваюсь с некоторыми проблемами, когда хочу замкнуть видео петлю, когда я нажимаю кнопку, вот функция, отвечающая за обнаружение: 

 def connect(self):
    break_flag = False
    MODEL_NAME = 'inference_graph'
    VIDEO_NAME = 'testing1.mp4'

    # Grab path to current working directory
    CWD_PATH = os.getcwd()

    # Path to frozen detection graph .pb file, which contains the model that is used
    # for object detection.
    PATH_TO_CKPT = os.path.join(CWD_PATH, MODEL_NAME, 'frozen_inference_graph.pb')

    # Path to label map file
    PATH_TO_LABELS = os.path.join(CWD_PATH, 'training', 'labelmap.pbtxt')

    # Path to video
    PATH_TO_VIDEO = os.path.join(CWD_PATH, VIDEO_NAME)

    # Number of classes the object detector can identify
    NUM_CLASSES = 1

    # Load the label map.
    # Label maps map indices to category names, so that when our convolution
    # network predicts `5`, we know that this corresponds to `king`.
    # Here we use internal utility functions, but anything that returns a
    # dictionary mapping integers to appropriate string labels would be fine
    label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
    categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
                                                                use_display_name=True)
    category_index = label_map_util.create_category_index(categories)

    # Load the Tensorflow model into memory.
    detection_graph = tf.Graph()
    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
            serialized_graph = fid.read()
            od_graph_def.ParseFromString(serialized_graph)
            tf.import_graph_def(od_graph_def, name='')

        sess = tf.Session(graph=detection_graph)

    # Define input and output tensors (i.e. data) for the object detection classifier

    # Input tensor is the image
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

    # Output tensors are the detection boxes, scores, and classes
    # Each box represents a part of the image where a particular object was detected
    detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

    # Each score represents level of confidence for each of the objects.
    # The score is shown on the result image, together with the class label.
    detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
    detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')

    # Number of objects detected
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')

    # Open video file
    video = cv2.VideoCapture('testing1.mp4')



    while(video.isOpened() and break_flag):

        # Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
        # i.e. a single-column array, where each item in the column has the pixel RGB value
        ret, frame = video.read()

        frame_expanded = np.expand_dims(frame, axis=0)

        # Perform the actual detection by running the model with the image as input
        (boxes, scores, classes, num) = sess.run(
            [detection_boxes, detection_scores, detection_classes, num_detections],
            feed_dict={image_tensor: frame_expanded})

        # Draw the results of the detection (aka 'visulaize the results')
        vis_util.visualize_boxes_and_labels_on_image_array(
            frame,
            np.squeeze(boxes),
            np.squeeze(classes).astype(np.int32),
            np.squeeze(scores),
            category_index,
            use_normalized_coordinates=True,
            line_thickness=8,
            min_score_thresh=0.90)

        # All the results have been drawn on the frame, so it's time to display it.


        height, width, channel = frame.shape
        bytesPerLine = 3 * width
        qImg = QtGui.QImage(frame.data, width, height, bytesPerLine, QtGui.QImage.Format_RGB888).rgbSwapped()
        pixmap = QPixmap(qImg)
        self.label_6.setScaledContents(True)
        self.label_6.setPixmap(pixmap)

        for i, box in enumerate(np.squeeze(boxes)):
            if (np.squeeze(scores)[i] > 0.99):
                width = frame.shape[1]
                height = frame.shape[0]
                i = 1
                ymin = box[0] * height
                xmin = box[1] * width
                ymax = box[2] * height
                xmax = box[3] * width
                a, b, c, d = int(xmin), int(xmax), int(ymin), int(ymax)
                img = frame[c:d, a:b]
                x = ocr.main(img)
                list.append(x)
                self.listWidget.addItem(x)
        # Press 'q' to quit
          if break_flag==True
    cnt = Counter()
    for i in list :
        cnt[i] +=1
    print(cnt)
    c = cnt.most_common(1)[0][0]
    print(c)

    video.release()
    cv2.destroyAllWindows()

пользовательский интерфейс просто зависнет и не будет работать нормально. Я не хочу завершать функцию, потому что мне нужны данные для дальнейшей обработки, может кто-нибудь помочь

...