com.microsoft - WordConvEmbedding#
WordConvEmbedding - 1#
Version
domain: com.microsoft
since_version: 1
function:
support_level: SupportType.COMMON
shape inference: False
This version of the operator has been available since version 1 of domain com.microsoft.
Summary
Attributes
char_embedding_size - INT : Integer representing the embedding vector size for each char.If not provide, use the char embedding size of embedding vector.
conv_window_size - INT : This operator applies convolution to word from left to right with window equal to conv_window_size and stride to 1.Take word ‘example’ for example, with conv_window_size equal to 2, conv is applied to [ex],[xa], [am], [mp]…If not provide, use the first dimension of conv kernel shape.
embedding_size - INT : Integer representing the embedding vector size for each word.If not provide, use the filter size of conv weight
Inputs
Sequence (heterogeneous) - T:
W (heterogeneous) - T1:
B (heterogeneous) - T1:
C (heterogeneous) - T1:
Outputs
Y (heterogeneous) - T1:
Type Constraints
T in ( tensor(int32) ): Constrain to tensor(int32).
T1 in ( tensor(float) ): Constrain to tensor(float).
Examples