docs/torch/torch.nn/torch.nn.modules/torch.nn.modules.sparse

torch.nn.modules.sparse

Members list

Grouped members

nn_sparse

A simple lookup table that stores embeddings of a fixed dictionary and size.

This module is often used to store word embeddings and retrieve them using indices. The input to the module is a list of indices, and the output is the corresponding word embeddings.

Value parameters

embeddingDim: The size of each embedding vector
maxNorm: If given, each embedding vector with norm larger than maxNorm is renormalized to have norm maxNorm.
normType: The p of the p-norm to compute for the maxNorm option. Default 2.
numEmbeddings: Size of the dictionary of embeddings
paddingIdx: If specified, the entries at paddingIdx do not contribute to the gradient; therefore, the embedding vector at paddingIdx is not updated during training, i.e. it remains as a fixed "pad". For a newly constructed Embedding, the embedding vector at paddingIdx will default to all zeros, but can be updated to another value to be used as the padding vector.
scaleGradByFreq: If given, this will scale gradients by the inverse of frequency of the words in the mini-batch. Default false.
sparse: If True, gradient w.r.t. weight matrix will be a sparse tensor. See Notes for more details regarding sparse gradients.

Attributes

See also: See Pytorch C++ Embedding

See Pytorch Python Embedding
Source: Embedding.scala
Supertypes: trait TensorModuleBase[Int64, ParamType]

trait Tensor[Int64] => Tensor[ParamType]

trait HasWeight[ParamType]

trait HasParams[ParamType]

class Module

class Object

trait Matchable

class Any
Show all

In this article

Generated with