Tensorflow Object Detection API: printing class detection as terminal output

Question

I have a simple question, but I cannot figure out how to do this. I use the TF Object Detection API to detect images, it works fine, and with the image in mind, it will draw a bounding box with a label and a trust estimate of which class it considers detected. My question is how can I print the detected class (as a string) and the count on the terminal, i.e. not only in the image, but also as output to the terminal, too.

Below is the code responsible for image detection

with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    for image_path in TEST_IMAGE_PATHS:
      image = Image.open(image_path)
      # the array based representation of the image will be used later in order to prepare the
      # result image with boxes and labels on it.
      image_np = load_image_into_numpy_array(image)
      # 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})
      # 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, min_score_thresh=.2)
      plt.figure(figsize=IMAGE_SIZE)
      plt.imshow(image_np)
      plt.show()

Thanks in advance, first stack overflow message, so please be careful with me

Answer 1

, . classes category_index, dict, - :

with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
for image_path in TEST_IMAGE_PATHS:
  image = Image.open(image_path)
  # the array based representation of the image will be used later in order to prepare the
  # result image with boxes and labels on it.
  image_np = load_image_into_numpy_array(image)
  # 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})

  # Here output the category as string and score to terminal
  print([category_index.get(i) for i in classes[0]])
  print(scores)

Answer 2

utils object_detection script visualization_utils.py. , visualize_boxes_and_labels_on_image_array, , _ (print (class_name)). .

Answer 3

Dat Omar.. . , 100 . 2-3 ( ). , ? , ? ( , ).

Answer 4

. TF Version 1.12.0 - .

.. \models\research\object_detection\utils\visualization_utils.py def visualize_boxes_and_labels_on_image_array for.

display_str , display_str ( 21, ), for, class_name, . - , , , .

  for i in range(min(max_boxes_to_draw, boxes.shape[0])):
    if scores is None or scores[i] > min_score_thresh:
      box = tuple(boxes[i].tolist())
      if instance_masks is not None:
        box_to_instance_masks_map[box] = instance_masks[i]
      if instance_boundaries is not None:
        box_to_instance_boundaries_map[box] = instance_boundaries[i]
      if keypoints is not None:
        box_to_keypoints_map[box].extend(keypoints[i])
      if scores is None:
        box_to_color_map[box] = groundtruth_box_visualization_color
      else:
        display_str = ''
        if not skip_labels:
          if not agnostic_mode:
            if classes[i] in category_index.keys():
              class_name = category_index[classes[i]]['name']
            else:
              class_name = 'N/A'
            display_str = str(class_name)
            print(display_str)
        if not skip_scores:
          if not display_str:
            display_str = '{}%'.format(int(100*scores[i]))
          else:
            display_str = '{}: {}%'.format(display_str, int(100*scores[i]))
        box_to_display_str_map[box].append(display_str)
        if agnostic_mode:
          box_to_color_map[box] = 'DarkOrange'
        else:
          box_to_color_map[box] = STANDARD_COLORS[
              classes[i] % len(STANDARD_COLORS)]
    #(print(class_name)) -- doesn't work : error, class name referenced before assignment

Answer 5

At first I was also confused. Got more than 100 boxes, whether only one was painted on my image. I agree with all the answers. Got my simple copy and paste solution for your infrecne.py:

    #assume you've got this in your inference.py
    vis_util.visualize_boxes_and_labels_on_image_array(
        image_np,
        output_dict['detection_boxes'],
        output_dict['detection_classes'],
        output_dict['detection_scores'],
        category_index,
        instance_masks=output_dict.get('detection_masks'),
        use_normalized_coordinates=True,
        line_thickness=8)

    # This is the way I'm getting my coordinates
    boxes = output_dict['detection_boxes']
    max_boxes_to_draw = boxes.shape[0]
    scores = output_dict['detection_scores']
    min_score_thresh=.5
    for i in range(min(max_boxes_to_draw, boxes.shape[0])):
        if scores is None or scores[i] > min_score_thresh:
            # boxes[i] is the box which will be drawn
            print ("This box is gonna get used", boxes[i])

Answer 6

@Dat Tran well, I used this print ([category_index.get (i) for I'm in classes [0]]) print (grades), but it does not print the detected classes, but prints all the classes that I gave