Mojo function

layer_norm

layer_norm[dtype: DType](input: Symbol, gamma: Symbol, beta: Symbol, epsilon: SIMD[dtype, 1]) -> Symbol

Performs layer normalization.

Args:

• ​input (Symbol): The input tensor to normalize.
• ​gamma (Symbol): The gamma parameter of the normalization.
• ​beta (Symbol): The beta parameter of the normalization.
• ​epsilon (SIMD[dtype, 1]): The epsilon parameter of the normalization.

Returns:

A symbolic tensor value with the normalization applied.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!
If you'd like to share more information, please report an issue on GitHub

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other