visualize boxes in tensorflow object detection

Question

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)
  # Actual detection.
  output_dict = run_inference_for_single_image(image_np, detection_graph)
  # Visualization of the results of a detection.
  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)
  plt.figure(figsize=IMAGE_SIZE)
  plt.imshow(image_np)

In one of the codes for tensorflow object detection API, there is the vis_util.visualize_boxes_and_labels_on_image_array method which draws bounding boxes on the image and returns the new image_np which is fed into plt.imshow(image_np) to display. However, vis_util.visualize_boxes_and_labels_on_image_array method is not assigned to image_np variable as shown in the code. How does plt.imshow(image_np) get the latest(The image which has the drawn bounding box) image?

But should it be image_np = vis_util.visualize_boxes_and_labels_on_image_array( ........... ), then the function can return the new modified content? — Ninja Dude
– Ninja Dude, Commented Feb 23, 2018 at 6:15
No. You are passing an array. The contents in the array (the image pixels) are modified. — MFisherKDX
– MFisherKDX, Commented Feb 23, 2018 at 6:17

MFisherKDX · Accepted Answer · 2018-02-23 06:15:59Z

2

You are passing the image_np value into visualize_boxes_and_labels_on_image_array as the first parameter and the function modifies its contents to draw the bounding boxes. The code is open source. You can check it out for yourself here.

answered Feb 23, 2018 at 6:15

MFisherKDX

2,8863 gold badges18 silver badges29 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

visualize boxes in tensorflow object detection

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related