ngraph::pass::BinarizeWeights Class Reference

This transformation converts weights to -1/+1 form and applies normalization factors to output low/high and after Convolution. For example, following graph. More...

#include <binarize_weights.hpp>

Inheritance diagram for ngraph::pass::BinarizeWeights:

Data Fields
	NGRAPH_RTTI_DECLARATION

Detailed Description

This transformation converts weights to -1/+1 form and applies normalization factors to output low/high and after Convolution. For example, following graph.

    .... ....  out_low  out_high           weights ..    ..  out_low out_high
      |    |      |        |                  |     |    |      |     |
     +--------------------------+           +--------------------------+
     | FakeQuantize (levels==2) |           | FakeQuantize (levels==2) |
     |     (on activations)     |           |       (on weights)       |
     +--------------------------+           +--------------------------+
                   |                                      |
                   |                                      |
                   -----------------    -------------------
                                   |    |
                                   v    v
                              +-------------+
                              | Convolution |
                              +-------------+
                                     |
                                     v

is transformed to:

             normalized normalized
    .... ....  out_low   out_high
      |    |      |         |
     +--------------------------+           +--------------------------+
     | FakeQuantize (levels==2) |           |         Constant         |
     |     (on activations)     |           | (with converted weights) |
     +--------------------------+           +--------------------------+
                   |                                      |
                   |                                      |
                   -----------------    -------------------
                                   |    |
                                   v    v
                              +-------------+
                              | Convolution |
                              +-------------+
                                     |
                                     v
                              +------------+     +---------------------------------------------------------------+
                              |  Multiply  | <---| Constant (normalization factor coming from FQ on activations) |
                              +------------+     +---------------------------------------------------------------+
                                     |
                                     v
                              +------------+     +-----------------------------------------------------------+
                              |  Multiply  | <---| Constant (normalization factor coming from FQ on weights) |
                              +------------+     +------------------------------------------------------------
                                     |
                                     v

Normalization factors are chosen based output_high value. If it's zero - norm factor is equal to output_low and output_high otherwise

---

The documentation for this class was generated from the following file:

• /home/jenkins/agent/workspace/openvino/documentation/upload_documentation/ovino_doc/build/_tmp_docs/openvino/inference-engine/src/transformations/include/transformations/common_optimizations/binarize_weights.hpp