Class ov::pass::low_precision::PullTransposeThroughDequantization#
-
class PullTransposeThroughDequantization : public ov::pass::MatcherPass#
PullTransposeThroughDequantization propagates dequantization operations through Transpose operations. The transformation is used on constant subgraph weights to prepare a model for the next low precision transformations.
For more details about the transformation, refer to PullTransposeThroughDequantization page in the OpenVINO Developer Guide.