TastyPancakes/Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

do things to docs

Browse Source
This commit is contained in:
Lyndon White 2019-02-27 12:20:44 +00:00
parent fcc3ec471a
commit c1a33c556f
1 changed files with 14 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
docs/src/models/layers.md
View File

@ -5,14 +5,16 @@ These core layers form the foundation of almost all neural networks.
```@docs ```@docs
Chain Chain
Dense Dense
```
## Convolution and Pooling Layers
These layers are used to build convolutional neural networks (CNNs).
```@docs
Conv Conv
MaxPool MaxPool
MeanPool MeanPool
```
## Additional Convolution Layers
```@docs
DepthwiseConv DepthwiseConv
ConvTranspose ConvTranspose
``` ```
@ -28,6 +30,13 @@ GRU
Flux.Recur Flux.Recur
``` ```
## Hipster Layers
These are marginally more obscure layers that you probably haven't heard of.
```@docs
MaxOut
```
## Activation Functions ## Activation Functions
Non-linearities that go between layers of your model. Most of these functions are defined in [NNlib](https://github.com/FluxML/NNlib.jl) but are available by default in Flux. Non-linearities that go between layers of your model. Most of these functions are defined in [NNlib](https://github.com/FluxML/NNlib.jl) but are available by default in Flux.