|
pulsatrix
|
Batch normalization (Ioffe & Szegedy, 2015) – per-channel statistics computed across the batch and spatial dimensions jointly, unlike GroupNormModule's per-(batch-row, group) statistics. More...


Go to the source code of this file.
Classes | |
| class | pulsatrix::BatchNormModule |
| y_{n,c,h,w} = gamma_c * (x_{n,c,h,w} - mu_c)/std_c + beta_c, mu_c/std_c computed per channel c over every (n, h, w) element jointly – BatchNorm's defining statistic, and the reason this module didn't exist before campaign_exai_dl_library_batch_dimension_support: it has nothing to compute over without a real batch dimension. Input/output are rank-4 (N, channels, H, W), the same convention Conv2DModule/GroupNormModule already establish. More... | |
Namespaces | |
| namespace | pulsatrix |
Batch normalization (Ioffe & Szegedy, 2015) – per-channel statistics computed across the batch and spatial dimensions jointly, unlike GroupNormModule's per-(batch-row, group) statistics.