nn_norm_broadcast: Reshape 1-D gamma/beta so they broadcast along the feature...
In ggmlR: 'GGML' Tensor Operations for Machine Learning
nn_norm_broadcast R Documentation
Reshape 1-D gamma/beta so they broadcast along the feature axis
Description
The feature axis moves with the input rank: an image is ggml
[W, H, C, N] (channels at ne[2]), a sequence is [size, seq, N]
(features at ne[0]), and a flat input needs no reshape at all.
Usage
nn_norm_broadcast(ctx, w, input_shape)
Arguments
ctx
A ggml_context.
w
A 1-D ggml_tensor of per-feature weights.
input_shape
The layer's input shape, in R order.
Value
w, reshaped to broadcast.
ggmlR documentation built on Oct. 23, 2026, 1:07 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
| nn_norm_broadcast | R Documentation |
Reshape 1-D gamma/beta so they broadcast along the feature axis
Description
The feature axis moves with the input rank: an image is ggml
[W, H, C, N] (channels at ne[2]), a sequence is [size, seq, N]
(features at ne[0]), and a flat input needs no reshape at all.
Usage
nn_norm_broadcast(ctx, w, input_shape)
Arguments
ctx |
A |
w |
A 1-D |
input_shape |
The layer's input shape, in R order. |
Value
w, reshaped to broadcast.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.