라즈베리파이안에서 코드와 코드를 결합하고 싶습니다

Question

import os def speak(option, msg) : os.system(&#34;espeak {} '{}'&#34;.format(option,msg)) option &#61; '-s 160 -p 95 -a 200 -v ko&#43;f3' msg &#61; '안녕하세요 반가워요' print('espeak', option, msg) speak(option,msg) import os import argparse import cv2 import numpy as np import sys import time from threading import Thread import importlib.util # Define VideoStream class to handle streaming of video from webcam in separate processing thread # Source - Adrian Rosebrock, PyImageSearch: https://www.pyimagesearch.com/2015/12/28/increasing-raspberry-pi-fps-with-python-and-opencv/ class VideoStream: &#34;&#34;&#34;Camera object that controls video streaming from the Picamera&#34;&#34;&#34; def __init__(self,resolution&#61;(640,480),framerate&#61;30): # Initialize the PiCamera and the camera image stream self.stream &#61; cv2.VideoCapture(0) ret &#61; self.stream.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG')) ret &#61; self.stream.set(3,resolution[0]) ret &#61; self.stream.set(4,resolution[1]) # Read first frame from the stream (self.grabbed, self.frame) &#61; self.stream.read() # Variable to control when the camera is stopped self.stopped &#61; False def start(self): # Start the thread that reads frames from the video stream Thread(target&#61;self.update,args&#61;()).start() return self def update(self): # Keep looping indefinitely until the thread is stopped while True: # If the camera is stopped, stop the thread if self.stopped: # Close camera resources self.stream.release() return # Otherwise, grab the next frame from the stream (self.grabbed, self.frame) &#61; self.stream.read() def read(self): # Return the most recent frame return self.frame def stop(self): # Indicate that the camera and thread should be stopped self.stopped &#61; True # Define and parse input arguments parser &#61; argparse.ArgumentParser() parser.add_argument('--modeldir', help&#61;'Folder the .tflite file is located in', required&#61;True) parser.add_argument('--graph', help&#61;'Name of the .tflite file, if different than detect.tflite', default&#61;'detect.tflite') parser.add_argument('--labels', help&#61;'Name of the labelmap file, if different than labelmap.txt', default&#61;'labelmap.txt') parser.add_argument('--threshold', help&#61;'Minimum confidence threshold for displaying detected objects', default&#61;0.5) parser.add_argument('--resolution', help&#61;'Desired webcam resolution in WxH. If the webcam does not support the resolution entered, errors may occur.', default&#61;'1280x720') parser.add_argument('--edgetpu', help&#61;'Use Coral Edge TPU Accelerator to speed up detection', action&#61;'store_true') args &#61; parser.parse_args() MODEL_NAME &#61; args.modeldir GRAPH_NAME &#61; args.graph LABELMAP_NAME &#61; args.labels min_conf_threshold &#61; float(args.threshold) resW, resH &#61; args.resolution.split('x') imW, imH &#61; int(resW), int(resH) use_TPU &#61; args.edgetpu # Import TensorFlow libraries # If tflite_runtime is installed, import interpreter from tflite_runtime, else import from regular tensorflow # If using Coral Edge TPU, import the load_delegate library pkg &#61; importlib.util.find_spec('tflite_runtime') if pkg: from tflite_runtime.interpreter import Interpreter if use_TPU: from tflite_runtime.interpreter import load_delegate else: from tensorflow.lite.python.interpreter import Interpreter if use_TPU: from tensorflow.lite.python.interpreter import load_delegate # If using Edge TPU, assign filename for Edge TPU model if use_TPU: # If user has specified the name of the .tflite file, use that name, otherwise use default 'edgetpu.tflite' if (GRAPH_NAME &#61;&#61; 'detect.tflite'): GRAPH_NAME &#61; 'edgetpu.tflite' # Get path to current working directory CWD_PATH &#61; os.getcwd() # Path to .tflite file, which contains the model that is used for object detection PATH_TO_CKPT &#61; os.path.join(CWD_PATH,MODEL_NAME,GRAPH_NAME) # Path to label map file PATH_TO_LABELS &#61; os.path.join(CWD_PATH,MODEL_NAME,LABELMAP_NAME) # Load the label map with open(PATH_TO_LABELS, 'r') as f: labels &#61; [line.strip() for line in f.readlines()] # Have to do a weird fix for label map if using the COCO &#34;starter model&#34; from # https://www.tensorflow.org/lite/models/object_detection/overview # First label is '???', which has to be removed. if labels[0] &#61;&#61; '???': del(labels[0]) # Load the Tensorflow Lite model. # If using Edge TPU, use special load_delegate argument if use_TPU: interpreter &#61; Interpreter(model_path&#61;PATH_TO_CKPT, experimental_delegates&#61;[load_delegate('libedgetpu.so.1.0')]) print(PATH_TO_CKPT) else: interpreter &#61; Interpreter(model_path&#61;PATH_TO_CKPT) interpreter.allocate_tensors() # Get model details input_details &#61; interpreter.get_input_details() output_details &#61; interpreter.get_output_details() height &#61; input_details[0]['shape'][1] width &#61; input_details[0]['shape'][2] floating_model &#61; (input_details[0]['dtype'] &#61;&#61; np.float32) input_mean &#61; 127.5 input_std &#61; 127.5 # Check output layer name to determine if this model was created with TF2 or TF1, # because outputs are ordered differently for TF2 and TF1 models outname &#61; output_details[0]['name'] if ('StatefulPartitionedCall' in outname): # This is a TF2 model boxes_idx, classes_idx, scores_idx &#61; 1, 3, 0 else: # This is a TF1 model boxes_idx, classes_idx, scores_idx &#61; 0, 1, 2 # Initialize frame rate calculation frame_rate_calc &#61; 1 freq &#61; cv2.getTickFrequency() # Initialize video stream videostream &#61; VideoStream(resolution&#61;(imW,imH),framerate&#61;30).start() time.sleep(1) #for frame1 in camera.capture_continuous(rawCapture, format&#61;&#34;bgr&#34;,use_video_port&#61;True): while True: # Start timer (for calculating frame rate) t1 &#61; cv2.getTickCount() # Grab frame from video stream frame1 &#61; videostream.read() # Acquire frame and resize to expected shape [1xHxWx3] frame &#61; frame1.copy() frame_rgb &#61; cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) frame_resized &#61; cv2.resize(frame_rgb, (width, height)) input_data &#61; np.expand_dims(frame_resized, axis&#61;0) # Normalize pixel values if using a floating model (i.e. if model is non-quantized) if floating_model: input_data &#61; (np.float32(input_data) - input_mean) / input_std # Perform the actual detection by running the model with the image as input interpreter.set_tensor(input_details[0]['index'],input_data) interpreter.invoke() # Retrieve detection results boxes &#61; interpreter.get_tensor(output_details[boxes_idx]['index'])[0] # Bounding box coordinates of detected objects classes &#61; interpreter.get_tensor(output_details[classes_idx]['index'])[0] # Class index of detected objects scores &#61; interpreter.get_tensor(output_details[scores_idx]['index'])[0] # Confidence of detected objects # Loop over all detections and draw detection box if confidence is above minimum threshold for i in range(len(scores)): if ((scores[i] > min_conf_threshold) and (scores[i] <&#61; 1.0)): # Get bounding box coordinates and draw box # Interpreter can return coordinates that are outside of image dimensions, need to force them to be within image using max() and min() ymin &#61; int(max(1,(boxes[i][0] * imH))) xmin &#61; int(max(1,(boxes[i][1] * imW))) ymax &#61; int(min(imH,(boxes[i][2] * imH))) xmax &#61; int(min(imW,(boxes[i][3] * imW))) cv2.rectangle(frame, (xmin,ymin), (xmax,ymax), (10, 255, 0), 2) # Draw label object_name &#61; labels[int(classes[i])] # Look up object name from &#34;labels&#34; array using class index label &#61; '%s: %d%%' % (object_name, int(scores[i]*100)) # Example: 'person: 72%' labelSize, baseLine &#61; cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2) # Get font size label_ymin &#61; max(ymin, labelSize[1] &#43; 10) # Make sure not to draw label too close to top of window cv2.rectangle(frame, (xmin, label_ymin-labelSize[1]-10), (xmin&#43;labelSize[0], label_ymin&#43;baseLine-10), (255, 255, 255), cv2.FILLED) # Draw white box to put label text in cv2.putText(frame, label, (xmin, label_ymin-7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2) # Draw label text # Draw framerate in corner of frame cv2.putText(frame,'FPS: {0:.2f}'.format(frame_rate_calc),(30,50),cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,0),2,cv2.LINE_AA) # All the results have been drawn on the frame, so it's time to display it. cv2.imshow('Object detector', frame) # Calculate framerate t2 &#61; cv2.getTickCount() time1 &#61; (t2-t1)/freq frame_rate_calc&#61; 1/time1 # Press 'q' to quit if cv2.waitKey(1) &#61;&#61; ord('q'): break # Clean up cv2.destroyAllWindows() videostream.stop()첫 번째는 espeak라는 tts를 사용하는 코드인데 저걸 이용하여두 번째 코드의 하단에 있는 #Draw label 부분을 읽게 하고 싶은데 캠 화면만 나오고 읽지를 못합니다. def speak(option, msg) : os.system(&#34;espeak {} '{}'&#34;.format(option,msg)) option &#61; '-s 160 -p 95 -a 200 -v ko&#43;f3' speak(option,msg)위의 코드에서 msg부분을 object_name 이나 classes로 바꿔도 보았고 스트링변수 asd를 선언하여 asd도 넣어보았지만 캠 화면에 나오는 label을 읽지못했습니다.어떻게 해야 목소리가 나올지 모르겠어서 질문 드립니다. 답변 해주시면 감사하겠습니다ㅠㅠ

라즈베리파이안에서 코드와 코드를 결합하고 싶습니다

0개의 답변

Q&A 목록