[嗨,我正在尝试构建一个具有两个按钮的用户界面,一个按钮将在while循环中打开,该循环读取视频并将其显示在屏幕上,而另一个是在不终止应用程序的情况下关闭循环这是代码示例:
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
cnt = Counter()
for i in list :
cnt[i] +=1
print(cnt)
c = cnt.most_common(1)[0][0]
print(c)
video.release()
cv2.destroyAllWindows()
现在我想创建一个函数来通过按UI上的按钮来打破循环
谁能帮我
您需要一个在按下按钮时更改其值的控制变量。如果满足条件,请检查循环中的变量并中断。
def read():
x = cv2.videoCapture(0)
while(video.isOpen()):
_ , frame = video.read
cv2.imshow("frame",frame)
if (break_flag == True): break
break_flag = False #reset the flag for the next run
您在按下按钮时调用的功能需要设置标志。
def on_button_pushed():
break_flag = True;
在这种情况下,您需要使用multithreading
。
from threading import Thread
...
read_thread = None
read_thread_run = False
# I rename your function
def read_frames():
global read_thread_run
x = cv2.videoCapture(0)
while video.isOpen() and read_thread_run:
_ , frame = video.read
cv2.imshow("frame",frame)
# When you click to play video
def click_read():
global read_thread
global read_thread_run
read_thread_run = True
read_thread = Thread(target=read_frames)
read_thread.start()
# When you click stop
def click_stop():
global read_thread
global read_thread_run
if read_thread is not None:
read_thread_run = False
read_thread.join()
我现在不知道您如何编码结构。您应该重写该示例以不使用函数的全局范围。
尝试: