fn
batch_norm_op
→TensorImplPtrint batch_norm_op(const int & x, const int & gamma, const int & beta, double eps, const int & running_mean, const int & running_var, double momentum)Python wrappers
Public Python APIs implemented by this engine symbol.Public entry point for 2-D Batch Normalization.
Applies training-mode batch normalization over the batch and spatial (height, width) axes. This is the most common batch-norm variant — used by virtually every CNN.
See Also
BatchNorm2dBackward : Autograd node implementing the forward + backward.
Parameters
xTensorImplPtrInput tensor of shape
(B, C, H, W).gammaTensorImplPtrPer-channel scale of shape
(C,).betaTensorImplPtrPer-channel shift of shape
(C,).epsdouble= NoneNumerical-stability constant. Default:
1e-5.Returns
TensorImplPtrNormalised output, same shape as x.