张量流中边界框的坐标

Question

我想要来自 tensorflow 模型的预测边界框的坐标。
我正在使用来自 here.
的对象检测脚本在遵循了一些关于 Whosebug 的答案后，我将最后一个检测块修改为

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.
  width, height = image.size
  print(width,height)
  ymin = output_dict['detection_boxes'][5][0]*height
  xmin = output_dict['detection_boxes'][5][1]*width
  ymax = output_dict['detection_boxes'][5][2]*height
  xmax = output_dict['detection_boxes'][5][3]*width
  #print(output_dict['detection_boxes'][0])
  print (xmin,ymin)
  print (xmax,ymax)

然而 output_dict['detection_boxes'].
中有 100 个元组即使对于那些未能预测的图像，也有 100 个元组

我要的是单张图片所有边界框的坐标

Answer 1

如果您检查所用模型的 pipeline.config 文件，您会发现在某些地方最大框数设置为 100。例如，在 config file of ssd_mobilenet_v1 中，这是演示笔记本中的模型，您可以在

下看到它

post_processing {
  batch_non_max_suppression {
    ...
    max_detections_per_class: 100
    max_total_detections: 100
  }
}

这也是输入阅读器的默认设置（对于训练和评估），您可以更改它们，但这仅与您 training/evaluating 相关。如果您想在不重新训练模型的情况下进行推理，您可以简单地使用预训练模型（同样，例如 ssd_mobilenet_v1），然后在使用 --config_override 参数时自己 exporting 它为了改变我上面在NMS中提到的值。

Answer 2

在 expand_dims 行之后，您可以添加这些代码。 filtered_boxes 变量将给出预测值大于 0.5 的边界框。

  (boxes, scores, classes, num) = sess.run(
      [detection_boxes, detection_scores, detection_classes, num_detections],
      feed_dict={image_tensor: image_np_expanded})
  indexes = []
  import os
  for i in range (classes.size):
    if(classes[0][i] in range(1,91) and scores[0][i]>0.5):
        indexes.append(i)
  filtered_boxes = boxes[0][indexes, ...]
  filtered_scores = scores[0][indexes, ...]
  filtered_classes = classes[0][indexes, ...]
  filtered_classes = list(set(filtered_classes))
  filtered_classes = [int(i) for i in filtered_classes]

Answer 3

for image_path in TEST_IMAGE_PATHS:
  image_np = cv2.imread(image_path)
  # 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)

#if using cv2 to load image
(im_width, im_height) = image_np.shape[:2]

ymin = output_dict['detection_boxes'][0][0]*im_height
xmin = output_dict['detection_boxes'][0][1]*im_width
ymax = output_dict['detection_boxes'][0][2]*im_height
xmax = output_dict['detection_boxes'][0][3]*im_width

使用上面的代码，您将获得检测到的 class 所需的边界框坐标，该坐标位于第一个方括号指示的第 0 个位置。

张量流中边界框的坐标

coordinates of bounding box in tensorflow

python

python-3.x

tensorflow

object-detection-api