min_scale 和 max_scale 在 Tensorflow 对象检测的模型配置中 API

min_scale and max_scale in the model config of Tensorflow Object Detection API

Tensorflow object detection API里面有用于训练的模型配置文件,这个配置文件有min_scalemax_scale检测对象,默认分别设置为0.2和0.95, 我对这些参数有一些疑问:

These params are for detecting the size of objects?

好吧,是的,也不是。这些参数在 ssd_anchor_generator 定义中,它本身就是一个 anchor_generator。系统的那部分负责为进一步的框预测提供一些锚框。

If we set the input size of network=300x300 and min_scale=0.2, then the network is not able to detect the objects that have size smaller than 300x0.2 = 60 pixels?

没有。可检测对象的大小不仅与 min_scale(仅影响 anchor 生成)有关,还受例如网络训练数据、网络深度等的影响

As far as you know, the ssd_mobilenet_v2_coco has the problem for detecting the small objects, If we set the min_scale = 0.05 and train the network on small objects with the same model, Is it possible to detect small objects with size 300x0.05 = 15 pixels?

也许吧?这完全取决于您的数据。修改 min_scale 参数可能会有所帮助(实际上 select 这些参数的另一个范围可能有意义),但有必要对您的数据进行试验。