Added Convolution3D as a layer supporting the regularizers and constraints API. (#4673)
This commit is contained in:
parent
4871208f02
commit
4c1353c188
2
docs/templates/constraints.md
vendored
2
docs/templates/constraints.md
vendored
@ -2,7 +2,7 @@
|
||||
|
||||
Functions from the `constraints` module allow setting constraints (eg. non-negativity) on network parameters during optimization.
|
||||
|
||||
The penalties are applied on a per-layer basis. The exact API will depend on the layer, but the layers `Dense`, `TimeDistributedDense`, `MaxoutDense`, `Convolution1D` and `Convolution2D` have a unified API.
|
||||
The penalties are applied on a per-layer basis. The exact API will depend on the layer, but the layers `Dense`, `TimeDistributedDense`, `MaxoutDense`, `Convolution1D`, `Convolution2D` and `Convolution3D` have a unified API.
|
||||
|
||||
These layers expose 2 keyword arguments:
|
||||
|
||||
|
2
docs/templates/regularizers.md
vendored
2
docs/templates/regularizers.md
vendored
@ -2,7 +2,7 @@
|
||||
|
||||
Regularizers allow to apply penalties on layer parameters or layer activity during optimization. These penalties are incorporated in the loss function that the network optimizes.
|
||||
|
||||
The penalties are applied on a per-layer basis. The exact API will depend on the layer, but the layers `Dense`, `TimeDistributedDense`, `MaxoutDense`, `Convolution1D` and `Convolution2D` have a unified API.
|
||||
The penalties are applied on a per-layer basis. The exact API will depend on the layer, but the layers `Dense`, `TimeDistributedDense`, `MaxoutDense`, `Convolution1D`, `Convolution2D` and `Convolution3D` have a unified API.
|
||||
|
||||
These layers expose 3 keyword arguments:
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user