ForInLoveAting

> 我的转换脚本非常幼稚。它只是从骨架和头部分别提取重量。 > 我不确定我是否理解“推论会影响推论的结果”，将python转换为cpp不会影响结果。分数完全相同且更快。 Because our project is very demanding, but maskrcnn_benchmark framework is based on python to write, the speed is certainly not as fast as c++.So I saw...

> 该项目的速度不如您期望的那么快，需要更多的优化。 > 如果您需要更高的性能，速度和内存效率，我不建议您这样做。 Thank you very much for your reply, because our current reasoning and subsequent processing need more than two seconds, normally we need to do less than...

> So, you mean that faster rcnn's process must be under 1 second per many images? Yes, because our project requires that we compress the speed to 1 second or...

> 每秒多少图像？这实际上取决于图像的数量，主干类型，类的数量和nms大小。 > 如果您可以弥补精度下降的问题，那么调整超参数可以提高速度。 We're not doing it for video, we're doing it for photos, and we're going to be able to identify the defects in the image in less...

> 我认为您需要使用nms进行消融研究。NMS是速度的主要因素。 Thank you very much for your answer, which is very helpful to me.

> 检查此配置选项 > PRE_NMS_TOP_N_TEST：1000 > POST_NMS_TOP_N_TEST：1000 > FPN_POST_NMS_TOP_N_TEST：1000 I used the default value for this, but will this change affect the accuracy of the whole model, or some things are...

> 减少这些选项可能会降低准确性。但并非总是如此，当我对一半的NMS候选人进行测试时，它仅下降了0.01 mAP。因此，您必须调整并检查mAP。它不需要重新培训。 ok thranks for your information