Rookie_Chris

ok， I will upload a simple test code.

Yes, you are right. Thank you very much. @allenchen8210

This code just helps you learn to implement SSD using TensorRT. This one can't be used directly.

TRAINING @tianfanzhu

You need to implement the depthwise layer， too.

Yes， you need to implement the SoftmaxPlugin

Allright, you can verify that the result is correct.

You should modify the aspect ratio parameter of PriorBox Layer in pluginImplement.cpp

channel pruning

Hi， You can use TensorRT3.0 API （createSSDDetectionOutputPlugin） directly， and you can find it at NvInferPlugin.h.