python - 使用 tensorflow object detection api 计算检测到的对象数量

Question

我是 tensorflow 的新手。我对如何计算使用 TensorFlow Object Detection API 检测到的对象数量感到困惑？

# 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')

if image_np_expanded is not None:
    # Actual detection.
    (boxes, scores, classes, num_detections) = sess.run(
        [boxes, scores, classes, num_detections],
        feed_dict={image_tensor: image_np_expanded}
    )

因为 num_detections 是一个 numpy.ndarray 我试图检索它的长度但不起作用。

num_detections.size
>> 1

既不使用张量长度:

tf.size(num_detections, out_type=tf.int32)
>> 1

在我的例子中，检测到的对象数量不止一个。

Answer 1

我一直在做类似的过程，但工作流程不同。我重写了 object_detection 笔记本中的教程代码，如下所示。它捕获检测框、类别和概率的输出，并忽略任何通过推理的图像处理。对于我的情况，我将结果转储到一个 JSON 文件中并将它们导入到另一个程序中以完成我的分析(确定检测数量)但是如果 python 是你的东西我认为你可以处理“myResults”来得到你的答案。

myResults = collections.defaultdict(list)
for image_path in TEST_IMAGE_PATHS:
  if os.path.exists(image_path):  
    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.
    op=get_scores(
      output_dict['detection_boxes'],
      output_dict['detection_classes'],
      output_dict['detection_scores'],
      category_index,
      min_score_thresh=.2)
    myResults[image_path].append(op)