Add a feature of UniformQDQ - support CV/NLP model's OPs, includingConv, DepthwiseConv2D, MatMul, etc. Additional op support be added upon request.

[qgao007]

Type of Change

A feature of UniformQDQ

Description

A feature of UniformQDQ

• support CV/NLP model's OPs, includingConv, DepthwiseConv2D, MatMul, etc. Additional op support be added upon request.

Expected Behavior & Potential Risk

Generate a UniformQDQ int8 model. No foreseeable risk.

How has this PR been tested?

This PR is tested on selected models with representative ops from image-classfication, object detection, and nlp.

Dependency Change?

Need Tensorflow with qunit8-support.
https://github.com/intel-innersource/frameworks.ai.tensorflow.private-tensorflow/tree/mabuzain/add-quint8-support

[thuang6]

one general question, I saw the changes in both 2.x and 3.x folders, so this PR enables UniformQDQ supported in both 2.x and 3.x API?

[qgao007]

one general question, I saw the changes in both 2.x and 3.x folders, so this PR enables UniformQDQ supported in both 2.x and 3.x API?

Thanks @thuang6 for the question! We ran it in new pythonic 3.x API, assuming compatibility with 2.x. We will confirm this shortly with @nhatleSummer22

[qgao007]

loop in @ashahba and @mahmoud-abuzaina also.

[thuang6]

one general question, I saw the changes in both 2.x and 3.x folders, so this PR enables UniformQDQ supported in both 2.x and 3.x API?

Thanks @thuang6 for the question! We ran it in new pythonic 3.x API, assuming compatibility with 2.x. We will confirm this shortly with @nhatleSummer22

new feature is only expected to 3.x API.

Please note, 3.x has separated packaging for each framework, TF 3.x packing is listed below, which only contains common & tensorflow folder under neural_compressor. If the function relies on code in other 2.x folders, it does not work.

"neural_compressor_tf": {
"project_name": "neural_compressor_tf",
"include_packages": find_packages(
include=[
"neural_compressor.common",
"neural_compressor.common.",
"neural_compressor.tensorflow",
"neural_compressor.tensorflow.",
],
),
"package_data": {"": ["*.yaml"]},
"install_requires": fetch_requirements("requirements_tf.txt"),
},

[mahmoud-abuzaina]

Supporting only 3.x API is fine, we don't really need to depend on 2.x API.

[sachinmuradi]

@lvliang-intel Could you help merge this PR in master ? Thanks

[thuang6]

2.x API including related source/example/doc/test folders will be removed in coming release, so for this PR, pls only keep code for 3.x API and make sure it does not rely on any code in 2.x folder.

[sachinmuradi]

@qgao007 Can you take a look ?