Link and Chains

Chainer provides many Link implementations in the chainer.links package.

Note

Some of the links are originally defined in the chainer.functions namespace. They are still left in the namespace for backward compatibility, though it is strongly recommended to use them via the chainer.links package.

Learnable connections

chainer.links.Bias	Broadcasted elementwise summation with learnable parameters.
chainer.links.Bilinear	Bilinear layer that performs tensor multiplication.
chainer.links.ChildSumTreeLSTM	Child-Sum TreeLSTM unit.
chainer.links.Convolution1D	1-dimensional convolution layer.
chainer.links.Convolution2D	Two-dimensional convolutional layer.
chainer.links.Convolution3D	3-dimensional convolution layer.
chainer.links.ConvolutionND	N-dimensional convolution layer.
chainer.links.Deconvolution1D	1-dimensional deconvolution layer.
chainer.links.Deconvolution2D	Two dimensional deconvolution function.
chainer.links.Deconvolution3D	3-dimensional deconvolution layer.
chainer.links.DeconvolutionND	N-dimensional deconvolution function.
chainer.links.DeformableConvolution2D	Two-dimensional deformable convolutional layer.
chainer.links.DepthwiseConvolution2D	Two-dimensional depthwise convolutional layer.
chainer.links.DilatedConvolution2D	Two-dimensional dilated convolutional layer.
chainer.links.EmbedID	Efficient linear layer for one-hot input.
chainer.links.GRU	Stateful Gated Recurrent Unit function (GRU)
chainer.links.Highway	Highway module.
chainer.links.Inception	Inception module of GoogLeNet.
chainer.links.InceptionBN	Inception module of the new GoogLeNet with BatchNormalization.
chainer.links.Linear	Linear layer (a.k.a. fully-connected layer).
chainer.links.LocalConvolution2D	Two-dimensional local convolutional layer.
chainer.links.LSTM	Fully-connected LSTM layer.
chainer.links.MLPConvolution2D	Two-dimensional MLP convolution layer of Network in Network.
chainer.links.NaryTreeLSTM	N-ary TreeLSTM unit.
chainer.links.NStepBiGRU	Stacked Bi-directional GRU for sequences.
chainer.links.NStepBiLSTM	Stacked Bi-directional LSTM for sequences.
chainer.links.NStepBiRNNReLU	Stacked Bi-directional RNN for sequences.
chainer.links.NStepBiRNNTanh	Stacked Bi-directional RNN for sequences.
chainer.links.NStepGRU	Stacked Uni-directional GRU for sequences.
chainer.links.NStepLSTM	Stacked Uni-directional LSTM for sequences.
chainer.links.NStepRNNReLU	Stacked Uni-directional RNN for sequences.
chainer.links.NStepRNNTanh	Stacked Uni-directional RNN for sequences.
chainer.links.Parameter	Link that just holds a parameter and returns it.
chainer.links.Scale	Broadcasted elementwise product with learnable parameters.
chainer.links.StatefulGRU	Stateful Gated Recurrent Unit function (GRU).
chainer.links.StatelessGRU	Stateless Gated Recurrent Unit function (GRU).
chainer.links.StatefulMGU
chainer.links.StatelessMGU
chainer.links.StatefulPeepholeLSTM	Fully-connected LSTM layer with peephole connections.
chainer.links.StatefulZoneoutLSTM
chainer.links.StatelessLSTM	Stateless LSTM layer.

Activation/loss/normalization functions with parameters

chainer.links.BatchNormalization	Batch normalization layer on outputs of linear or convolution functions.
chainer.links.BatchRenormalization	Batch renormalization layer on outputs of linear or convolution functions.
chainer.links.GroupNormalization	Group normalization layer on outputs of convolution functions.
chainer.links.LayerNormalization	Layer normalization layer on outputs of linear functions.
chainer.links.BinaryHierarchicalSoftmax	Hierarchical softmax layer over binary tree.
chainer.links.BlackOut	BlackOut loss layer.
chainer.links.CRF1d	Linear-chain conditional random field loss layer.
chainer.links.SimplifiedDropconnect	Fully-connected layer with simplified dropconnect regularization.
chainer.links.PReLU	Parametric ReLU function as a link.
chainer.links.Swish	Swish activation function as a link.
chainer.links.Maxout	Fully-connected maxout layer.
chainer.links.NegativeSampling	Negative sampling loss layer.

Machine learning models

chainer.links.Classifier

A simple classifier model.

Pre-trained models

Pre-trained models are mainly used to achieve a good performance with a small dataset, or extract a semantic feature vector. Although CaffeFunction automatically loads a pre-trained model released as a caffemodel, the following link models provide an interface for automatically converting caffemodels, and easily extracting semantic feature vectors.

For example, to extract the feature vectors with VGG16Layers, which is a common pre-trained model in the field of image recognition, users need to write the following few lines:

from chainer.links import VGG16Layers
from PIL import Image

model = VGG16Layers()
img = Image.open("path/to/image.jpg")
feature = model.extract([img], layers=["fc7"])["fc7"]

where fc7 denotes a layer before the last fully-connected layer. Unlike the usual links, these classes automatically load all the parameters from the pre-trained models during initialization.

VGG Networks

chainer.links.VGG16Layers	A pre-trained CNN model with 16 layers provided by VGG team.
chainer.links.VGG19Layers	A pre-trained CNN model with 19 layers provided by VGG team.
chainer.links.model.vision.vgg.prepare	Converts the given image to the numpy array for VGG models.

GoogLeNet

chainer.links.GoogLeNet	A pre-trained GoogLeNet model provided by BVLC.
chainer.links.model.vision.googlenet.prepare	Converts the given image to the numpy array for GoogLeNet.

Residual Networks

chainer.links.model.vision.resnet.ResNetLayers	A pre-trained CNN model provided by MSRA.
chainer.links.ResNet50Layers	A pre-trained CNN model with 50 layers provided by MSRA.
chainer.links.ResNet101Layers	A pre-trained CNN model with 101 layers provided by MSRA.
chainer.links.ResNet152Layers	A pre-trained CNN model with 152 layers provided by MSRA.
chainer.links.model.vision.resnet.prepare	Converts the given image to the numpy array for ResNets.

Compatibility with other frameworks

chainer.links.TheanoFunction	Theano function wrapper.
chainer.links.caffe.CaffeFunction	Caffe emulator based on the model file of Caffe.

Link and Chain base classes

chainer.Link	Building block of model definitions.
chainer.Chain	Composable link with object-like interface.
chainer.ChainList	Composable link with list-like interface.
chainer.Sequential	Sequential model which has a single-stream forward pass.

Link hooks

Chainer provides a link-hook mechanism that enriches the behavior of Link. You can implement your own link-hook to inject arbitrary code before/after the forward propagation.

chainer.LinkHook

Base class of hooks for links.