How can I applied box function to detect face in colab?

[zoro_kun]

hi , I am new to python I trying to give the prediction output with box that detect human face but after I run the video not have the box so how can I applied it in the codes?

def prediction (filepath):
  input_shape = (128, 128, 3)
  pr_data = []
  detector = dlib.get_frontal_face_detector()
  cap = cv2.VideoCapture(filepath)
  frameRate = cap.get(5)
  while cap.isOpened():
      frameId = cap.get(1)
      ret, frame = cap.read()
      if ret != True:
          break
      if frameId % ((int(frameRate)+1)*1) == 0:
          face_rects, scores, idx = detector.run(frame, 0)
          for i, d in enumerate(face_rects):
              x1 = d.left()
              y1 = d.top()
              x2 = d.right()
              y2 = d.bottom()
              crop_img = frame[y1:y2, x1:x2]
              data = img_to_array(cv2.resize(crop_img, (128, 128))).flatten() / 255.0
              data = data.reshape(-1, 128, 128, 3)
              print((model.predict(data) > 0.5).astype("int32"))
              outt=''
  if ((model.predict(data) > 0.5).astype("int32")[0][0] == 0 ):
    return 'Real'
  else:
    return 'Fake'

[emmafrost1]

@emmafrost1

In this code, the cv2.rectangle function is used to draw a green rectangle around each detected face, and the cv2.putText function, is used to write the prediction label (Real or Fake) on top of each rectangle. The parameters for cv2.rectangle are the input frame, the top-left and bottom-right coordinates of the rectangle, the color (in BGR format), and the thickness of the rectangle. The parameters for cv2.putText are the input frame, the text to be written, the bottom-left corner of the text, the font type, the font scale, the color, and the thickness.

Note that I added cap.release() and cv2.destroyAllWindows() at the end of the function to release the video capture and destroy all windows once the video processing is done.

Hi buddy, did this work for you?

[berak]

@emmafrost1

cv2.destroyAllWindows()

please note, that opencv’s gui functions are unavailable on colab (maybe write image to disk ?)

[zoro_kun]

hi sorry, I’m new with this. where I need to input cv2.rectangle and cv2.putText? after y2 = d.bottom()? or before x1 = d.left().