Why is it the `BatchNorm2d ` layers in a frozen model trainable?

[menocineto]

Why are BatchNorm layers set to trainable in a frozen model

Someone asked this question already but I could not find an intuitive explanation. Hence thought of opening a new topic thread. here is the link to the original post https://forums.fast.ai/t/why-is-it-the-batchnorm2d-layers-in-a-frozen-model-trainable/38944/2 My understanding is by default when we create a learner object from a model and data bunch the underlying network architecture’s layers are frozen except the custom layer that is added for the specific classification problem. learn = cn…