Flux.jl/docs/src/models/layers.md
2019-10-09 21:36:40 +05:30

79 lines
1.4 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

## Basic Layers
These core layers form the foundation of almost all neural networks.
```@docs
Chain
Dense
```
## Convolution and Pooling Layers
These layers are used to build convolutional neural networks (CNNs).
```@docs
Conv
MaxPool
MeanPool
DepthwiseConv
ConvTranspose
CrossCor
```
## Recurrent Layers
Much like the core layers above, but can be used to process sequence data (as well as other kinds of structured data).
```@docs
RNN
LSTM
GRU
Flux.Recur
```
## Other General Purpose Layers
These are marginally more obscure than the Basic Layers.
But in contrast to the layers described in the other sections are not readily grouped around a particular purpose (e.g. CNNs or RNNs).
```@docs
Maxout
SkipConnection
```
## 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.
Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call `σ.(xs)`, `relu.(xs)` and so on.
```@docs
σ
relu
leakyrelu
elu
swish
```
## Normalisation & Regularisation
These layers don't affect the structure of the network but may improve training times or reduce overfitting.
```@docs
BatchNorm
Dropout
AlphaDropout
LayerNorm
GroupNorm
```
## Loss Functions
```@docs
mse
crossentropy
logitcrossentropy
binarycrossentropy
logitbinarycrossentropy
kldivergence
poisson
hinge
```