caffe，deeplab,对Interp（差值）层的理解

更详细的参数解释查阅interp_layer.cpp。

prototxt中的用法:

layer{
  bottom:"input"
  top:"output"
  name:"interp_layer"
  type:"Interp"
  interp_param{
     shrink_factor:4
     zoom_factor:3
     pad_beg:0
     pad_end:0
}

interp_layer.cpp相关片段

#读入图片的高度和宽度
 height_in_ = bottom[0]->height();
 width_in_ = bottom[0]->width();

#根据设定参数调整后的高度，pad_beg,pad_end只能设置成0及0以下。
 height_in_eff_ = height_in_ + pad_beg_ + pad_end_;
 width_in_eff_ = width_in_ + pad_beg_ + pad_end_;

#interp的顺序是先缩小，再放大
 height_out_ = (height_in_eff_ - 1) / shrink_factor + 1;
 width_out_ = (width_in_eff_ - 1) / shrink_factor + 1;
 height_out_ = height_out_ + (height_out_ - 1) * (zoom_factor - 1);
 width_out_ = width_out_ + (width_out_ - 1) * (zoom_factor - 1);