how to copy the weights for Batch_Normalization layer in Network API as there is no corresponding layer for it ?

I am trying to populate the network again using Network API and cannot find anything for batch normalization.

any suggestion?

Hello,

You can use a Scale layer in place of batch normalization layer. Please reference: https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/c_api/classnvinfer1_1_1_i_scale_layer.html

the batch normalization layer is having both weights and bias. I am confused how to utilize them because I cant see any parameter for that. I will be thankful if you can provide an example for python API.

thanks