Refactor Keras PTQ Implementation

[zehao-intel]

Type of Change

Feature

Description

Refactor Keras PTQ implementation from json conversion to layer replacement on INC TF 3.0 New API.
The Keras3 Support will be removed because qint8 tensor is not supported as input of layer.call.

How has this PR been tested?

UT

Dependency Change?

No

[github-actions]

⚡ Required checks status: All passing 🟢

Groups summary

🟢 Code Scan Tests workflow

Check ID	Status	Error details
Code-Scan	success		✅
Code-Scan (Bandit Code Scan Bandit)	success		✅
Code-Scan (DocStyle Code Scan DocStyle)	success		✅
Code-Scan (Pylint Code Scan Pylint)	success		✅

These checks are required after the changes to neural_compressor/tensorflow/algorithms/static_quant/keras.py, neural_compressor/tensorflow/keras/layers/__init__.py, neural_compressor/tensorflow/keras/layers/conv2d.py, neural_compressor/tensorflow/keras/layers/dense.py, neural_compressor/tensorflow/keras/layers/depthwise_conv2d.py, neural_compressor/tensorflow/keras/layers/layer_initializer.py, neural_compressor/tensorflow/keras/layers/pool2d.py, neural_compressor/tensorflow/keras/layers/quantizer.py, neural_compressor/tensorflow/keras/layers/separable_conv2d.py, neural_compressor/tensorflow/keras/quantization/config.py.

🟢 Unit Tests 3x-TensorFlow workflow

Check ID	Status	Error details
UT-3x-TensorFlow	success		✅
UT-3x-TensorFlow (Coverage Compare CollectDatafiles)	success		✅
UT-3x-TensorFlow (Unit Test 3x TensorFlow Unit Test 3x TensorFlow)	success		✅
UT-3x-TensorFlow (Unit Test 3x TensorFlow baseline Unit Test 3x TensorFlow baseline)	success		✅

These checks are required after the changes to neural_compressor/tensorflow/algorithms/static_quant/keras.py, neural_compressor/tensorflow/keras/layers/__init__.py, neural_compressor/tensorflow/keras/layers/conv2d.py, neural_compressor/tensorflow/keras/layers/dense.py, neural_compressor/tensorflow/keras/layers/depthwise_conv2d.py, neural_compressor/tensorflow/keras/layers/layer_initializer.py, neural_compressor/tensorflow/keras/layers/pool2d.py, neural_compressor/tensorflow/keras/layers/quantizer.py, neural_compressor/tensorflow/keras/layers/separable_conv2d.py, neural_compressor/tensorflow/keras/quantization/config.py, test/3x/tensorflow/keras/test_config.py, test/3x/tensorflow/quantization/test_smooth_quant.py, test/3x/tensorflow/test_autotune.py, requirements_tf.txt.

---

Thank you for your contribution! 💜

Note
This comment is automatically generated and will be updates every 180 seconds within the next 6 hours. If you have any other questions, contact chensuyue or XuehaoSun for help.