@Diyar

Как запустить определенный код в другом потоке?

# import the necessary packages
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from os.path import dirname, join
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import imutils
import time
import cv2
import os
import time
from threading import Thread

import pyttsx3
text = 'Маска есть спасибо'
text2 = 'Наденьте маску'
tts = pyttsx3.init()
rate = tts.getProperty('rate') #Скорость произношения
tts.setProperty('rate', rate-40)
volume = tts.getProperty('volume') #Громкость голоса
tts.setProperty('volume', volume+0.9)
voices = tts.getProperty('voices')
# Задать голос по умолчанию
tts.setProperty('voice', 'ru') 
# Попробовать установить предпочтительный голос
for voice in voices:
    if voice.name == 'Anna':
        tts.setProperty('voice', voice.id)




		



def detect_and_predict_mask(frame, faceNet, maskNet):
	# grab the dimensions of the frame and then construct a blob
	# from it
	(h, w) = frame.shape[:2]
	blob = cv2.dnn.blobFromImage(frame, 1.0, (224, 224),
		(104.0, 177.0, 123.0))

	# pass the blob through the network and obtain the face detections
	faceNet.setInput(blob)
	detections = faceNet.forward()
	print(detections.shape)

	# initialize our list of faces, their corresponding locations,
	# and the list of predictions from our face mask network
	faces = []
	locs = []
	preds = []

	# loop over the detections
	for i in range(0, detections.shape[2]):
		# extract the confidence (i.e., probability) associated with
		# the detection
		confidence = detections[0, 0, i, 2]

		# filter out weak detections by ensuring the confidence is
		# greater than the minimum confidence
		if confidence > 0.5:
			# compute the (x, y)-coordinates of the bounding box for
			# the object
			box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
			(startX, startY, endX, endY) = box.astype("int")

			# ensure the bounding boxes fall within the dimensions of
			# the frame
			(startX, startY) = (max(0, startX), max(0, startY))
			(endX, endY) = (min(w - 1, endX), min(h - 1, endY))

			# extract the face ROI, convert it from BGR to RGB channel
			# ordering, resize it to 224x224, and preprocess it
			face = frame[startY:endY, startX:endX]
			try:
				face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
				face = cv2.resize(face, (224, 224))
				face = img_to_array(face)
				face = preprocess_input(face)
				faces.append(face)
				locs.append((startX, startY, endX, endY))
			except Exception:
				print("")
			# add the face and bounding boxes to their respective
			# lists
			
			

	# only make a predictions if at least one face was detected
	if len(faces) > 0:
		# for faster inference we'll make batch predictions on *all*
		# faces at the same time rather than one-by-one predictions
		# in the above `for` loop
		try:
			faces = np.array(faces, dtype="float32")
		except Exception:
			print("")
		preds = maskNet.predict(faces, batch_size=32)

	# return a 2-tuple of the face locations and their corresponding
	# locations
	return (locs, preds)

# load our serialized face detector model from disk
prototxtPath = r"deploy.protext"
weightsPath = r"res10_300x300_ssd_iter_140000.caffemodel"
faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)

# load the face mask detector model from disk
maskNet = load_model("mask_detector.model")

# initialize the video stream
print("Starting the CAMERA...")
vs = VideoStream(src=0).start()

# loop over the frames from the video stream
while True:
	# grab the frame from the threaded video stream and resize it
	# to have a maximum width of 400 pixels
	frame = vs.read()
	frame = imutils.resize(frame, width=400)

	# detect faces in the frame and determine if they are wearing a
	# face mask or not
	(locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)

	# loop over the detected face locations and their corresponding
	# locations
	
	for (box, pred) in zip(locs, preds):
		# unpack the bounding box and predictions
		(startX, startY, endX, endY) = box
		(mask, withoutMask) = pred

		# determine the class label and color we'll use to draw
		# the bounding box and text
		label = "Mask" if mask > withoutMask else "No Mask"
		color = (0, 255, 0) if label == "Mask" else (0, 0, 255)
		if label == "Mask":
			tts.say(text)
			print("he")
		elif label == "No Mask":
			tts.say(text2)
			print("rr")
		tts.runAndWait()
			
			
		
		# include the probability in the label
		label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)

		# display the label and bounding box rectangle on the output
		# frame
		cv2.putText(frame, label, (startX, startY - 10),
			cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
		cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)

	# show the output frame
	cv2.imshow("Frame", frame)
	key = cv2.waitKey(1) & 0xFF

	# if the `q` key was pressed, break from the loop
	if key == ord("q"):
		break

# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()

Проблема кода начинается с if label == "Mask"
Как можно этот код сделать вторым потоком, чтобы при каждом кадре она не ждала когда синтез до конца скажет речь, а то в проге получается так что каждый кадр проверяет на наличии маски и в случае если есть или нет синтез озвучивает текст и потом уже поток продолжает обрабатывать кадр
  • Вопрос задан
  • 63 просмотра
Пригласить эксперта
Ответы на вопрос 1
@Vindicar
Модуль threading в помощь.
Кроме того, стоит запоминать, было ли найдено лицо на предыдущем кадре. Если на предыдущем не было, а на текущем есть, и если поток не активен, запускаем поток.
Ответ написан
Ваш ответ на вопрос

Войдите, чтобы написать ответ

Войти через центр авторизации
Похожие вопросы