我使用了https://github.com/tensorflow/models/tree/master/research/object_detection中的Tensorflow的对象检测API。我使用了summarize_graph，并验证了输出为detection_boxes，detection_scores，detection_classes和num_detections。
这些是什么？其中哪一个包含被检测物体的检测框的坐标？
我显示了每个输出的形状并找到了它们的大小：
detection_boxes.shape = (1,300,4) detection_scores.shape = (1, 300) detection_classes.shape = (1, 300) num_detections.shape = (1,) 在一张包含8张扑克牌的图像上进行测试时。所考虑的类别是数字A，2、3、4、5和6。
答案 0 :(得分：1)
They represent exactly what the names suggest:
detection_boxes: coordinates of the predicted objects. Usually they represent: xmin,xmax,ymin,ymax.
detection_scores: exactly the score of each prediction, i.e., the model is 69% sure that certain image represent a A card.
detection_classes: a label that represent the prediction.
num_detections: the number of detections that the model was able to predict given a certain threshold.