A primitive to perform batch normalization. More...
Classes | |
| struct | dnnl::batch_normalization_forward |
| Batch normalization for forward propagation. More... | |
| struct | dnnl::batch_normalization_backward |
| Batch normalization backward propagation. More... | |
A primitive to perform batch normalization.
Both forward and backward passes support in-place operation; that is, src and dst point to the same memory for forward pass, and diff_dst and diff_src point to the same memory for backward pass.
Batch normalization supports different flavors controlled by dnnl_batch_normalization_desc_t. For example, batch normalization can compute the mean and variance on its own or take them as inputs. It can either perform scaling and shifting using gamma and beta parameters or not. Optionally, it can also perform a fused ReLU, which in case of training would also require a workspace.