如果在 TensorFlow 对象检测 API 中检测到相同的对象，则仅打印一次类名

Question

我使用以下代码打印类名，但如果类名已经打印，我只需要一次类名。
例如，如果检测到一个人，则循环打印类名person。
仅当之前未检测到类名时，我才需要打印类名。

with detection_graph.as_default():
  with tf.compat.v1.Session(graph=detection_graph) as sess:
    while True:
        ret,image_np=cap.read()
      # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
        image_np_expanded = np.expand_dims(image_np, axis=0)
        image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
      # Each box represents a part of the image where a particular object was detected.
        boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
      # Each score represent how level of confidence for each of the objects.
      # Score is shown on the result image, together with the class label.
        scores = detection_graph.get_tensor_by_name('detection_scores:0')
        classes = detection_graph.get_tensor_by_name('detection_classes:0')
        num_detections = detection_graph.get_tensor_by_name('num_detections:0')
      # Actual detection.
        (boxes, scores, classes, num_detections) = sess.run(
          [boxes, scores, classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})
        a=[category_index.get(i) for i in classes[0]]
        x=a[0]
        y=x['name']
        print(y)
        # Visualization of the results of a detection.
        vis_util.visualize_boxes_and_labels_on_image_array(
          image_np,
          np.squeeze(boxes),
          np.squeeze(classes).astype(np.int32),
          np.squeeze(scores),
          category_index,
          use_normalized_coordinates=True,
          line_thickness=8)
        cv2.imshow('object detection',cv2.resize(image_np,(800,600)))
        if cv2.waitKey(25) & 0xFF == ord('q'):
          cv2.destroyAllWindows()
          break

Answer 1

您可以通过在 while 循环之前创建一个列表对象并根据条件附加类名来做到这一点。

我已经修改了你的代码，条件是只打印一次类名。

with detection_graph.as_default():
  with tf.compat.v1.Session(graph=detection_graph) as sess:
    present = []
    while True:
        ret,image_np=cap.read()
      # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
        image_np_expanded = np.expand_dims(image_np, axis=0)
        image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
      # Each box represents a part of the image where a particular object was detected.
        boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
      # Each score represent how level of confidence for each of the objects.
      # Score is shown on the result image, together with the class label.
        scores = detection_graph.get_tensor_by_name('detection_scores:0')
        classes = detection_graph.get_tensor_by_name('detection_classes:0')
        num_detections = detection_graph.get_tensor_by_name('num_detections:0')
      # Actual detection.
        (boxes, scores, classes, num_detections) = sess.run(
          [boxes, scores, classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})
        a=[category_index.get(i) for i in classes[0]]
        x=a[0]
        y=x['name']
        if y in present:
          pass
        else:
          present.append(y)
          print(y)
        # Visualization of the results of a detection.
        vis_util.visualize_boxes_and_labels_on_image_array(
          image_np,
          np.squeeze(boxes),
          np.squeeze(classes).astype(np.int32),
          np.squeeze(scores),
          category_index,
          use_normalized_coordinates=True,
          line_thickness=8)
        cv2.imshow('object detection',cv2.resize(image_np,(800,600)))
        if cv2.waitKey(25) & 0xFF == ord('q'):
          cv2.destroyAllWindows()
          break  

我希望这能回答您的问题。快乐学习！