I have a TFLite model that contains a FusedBatchNorm operation that seems to be fused with a Conv2d operation. I am trying to reproduce the output of that operation, however, I am not able to do that without knowing the fused_batch_norm parameters (mean and variance) for that particular operation. Is there a way to extract the FusedBatchNorm or BatchNorm parameters (mean and variance) from the TFLite model?

TFLite model attached metadata has mean and variance data for input layer only. I am interested in intermediate layers.

Interpreter.get_tensor_details() for inner layers don’t have any mean and variance parameters.