bitorch.layers.qembedding.QEmbedding

class bitorch.layers.qembedding.QEmbedding(*args: Any, embedding_dim: int, weight_quantization: Optional[Union[Quantization, str]] = None, output_quantization: Optional[Union[Quantization, str]] = None, **kwargs: Any)

Quantized version of pytorchs embedding layer. With input indices the embedding is computed with a quantized version of the layers weight table. The output embedding will be also quantized before return.

Methods

__init__	Initializes internal Module state, shared by both nn.Module and ScriptModule.
forward	generates embeddings for received bags.

Attributes

__init__(*args: Any, embedding_dim: int, weight_quantization: Optional[Union[Quantization, str]] = None, output_quantization: Optional[Union[Quantization, str]] = None, **kwargs: Any) → None

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(input: Tensor) → Tensor

generates embeddings for received bags. then quantizes these embeddings and depending on configuration forwards it through another quantized linear layer.

Parameters:

input (Tensor) – indices for embeddings

Returns:

embeddings for given sequences

Return type:

Tensor