Parsing a caffe normalize layer

Could anybody please tell me how to parse a caffe normalize(not batch-normalize) layer in TensorRT 5.0?
It looks like this:

layer {
  name: "conv4_3_norm"
  type: "Normalize"
  bottom: "conv4_3"
  top: "conv4_3_norm"
  norm_param {
    across_spatial: false
    scale_filler {
      type: "constant"
      value: 20.0
    }
    channel_shared: false
  }
}

I will really appreciate your help!

Hi, I need help with this too

Sorry for duplicate! I fixed the problem by adding these lines to my python code:

trt.init_libnvinfer_plugins(TRT_LOGGER, '')
PLUGIN_CREATORS = trt.get_plugin_registry().plugin_creator_list
2 Likes