[SSS Review] Develop XQuant Extension Tool

.github/workflows/build_docs.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/link_checker.yml

@@ -5,20 +5,18 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
   push:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
 
 jobs:
   link-checker:
-    if: github.repository == 'sony/model_optimization'
+    if: github.repository == 'SonySemiconductorSolutions/mct-model-optimization'
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     steps:
       - uses: actions/checkout@v4
       - name: Install Python 3
@@ -32,4 +30,4 @@ jobs:
       - name: Run unittests
         run: |
           export CURL_CA_BUNDLE=''
-          python -m unittest tests/doc_tests/test_docs_links.py -v
+          python -m unittest tests/doc_tests/test_docs_links.py -v

.github/workflows/nightly.yml

@@ -6,36 +6,36 @@
 
 jobs:
   build:
-    if: github.repository == 'sony/model_optimization' # Don't do this in forks
+    if: github.repository == 'SonySemiconductorSolutions/mct-model-optimization' # Don't do this in forks
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
       - name: Install Python 3
         uses: actions/setup-python@v5
         with:
           python-version: 3.12
 
 # To override mct-quantizers package with nightly version
 #      - name: Edit requirements mct-quantizers name # Remove the entire line in requirements.txt so no need special care for the specified version
 #        run: |
 #          sed -i "/mct-quantizers/c\mct-quantizers-nightly" requirements.txt
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install -r requirements.txt
           pip install twine
       - name: Build nightly
         run: |
           version=$(python -c 'import model_compression_toolkit; print(model_compression_toolkit.__version__)')
           now=$(date +'%Y%m%d.%H%M%S')
           echo "nightly_version=$version.$now" >> $GITHUB_ENV
           sed -i "s/__version__ =.*/__version__ = \"$version.$now\"/g" model_compression_toolkit/__init__.py
           sed -i "s/name='model_compression_toolkit'/name='mct-nightly'/g" setup.py
           python setup.py sdist bdist_wheel
       - name: Publish nightly
         run: |
           twine upload --repository pypi dist/* --verbose -u __token__ -p ${{ secrets.PYPI_API_SSI_DEV_NIGHTLY_KEY }}
       - name: Post publish import test
         run: |
           pip install mct-nightly tensorflow torch torchvision
           version=$(python -c 'import model_compression_toolkit; print(model_compression_toolkit.__version__)')

.github/workflows/run_tests_python310_keras214.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python310_keras215.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python310_pytorch23.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python310_pytorch24.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python310_pytorch25.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python310_pytorch26.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python311_keras214.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python311_keras215.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python311_pytorch23.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python311_pytorch24.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python311_pytorch25.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python311_pytorch26.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python312_pytorch23.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python312_pytorch24.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python312_pytorch25.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python312_pytorch26.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python39_keras214.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python39_keras215.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python39_pytorch23.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python39_pytorch24.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python39_pytorch25.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_python39_pytorch26.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

.github/workflows/run_tests_suite_coverage.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -14,7 +12,7 @@ concurrency:
 jobs:
   build:
     runs-on: ubuntu-latest
-    timeout-minutes: 80
+    timeout-minutes: 100
     env:
       COVERAGE_THRESHOLD: 98
     steps:

.github/workflows/tests_common.yml

@@ -4,8 +4,6 @@ on:
   schedule:
     - cron: 0 0 * * *
   pull_request:
-    branches:
-      - main
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}

README.md

@@ -1,6 +1,6 @@
 <div align="center" markdown="1">
 <p>
-      <a href="https://sony.github.io/model_optimization/" target="_blank">
+      <a href="https://sonysemiconductorsolutions.github.io/mct-model-optimization/" target="_blank">
         <img src="https://raw.githubusercontent.com/sony/model_optimization/refs/heads/main/docsrc/images/mctHeader1-cropped.svg" width="1000"></a>
 </p>
 
@@ -17,9 +17,9 @@ ______________________________________________________________________
   <a href="#license">License</a>
 </p>
 <p align="center">
-  <a href="https://sony.github.io/model_optimization#prerequisites"><img src="https://img.shields.io/badge/pytorch-2.3%20%7C%202.4%20%7C%202.5%20%7C%202.6-blue" /></a>
-  <a href="https://sony.github.io/model_optimization#prerequisites"><img src="https://img.shields.io/badge/tensorflow-2.14%20%7C%202.15-blue" /></a>
-  <a href="https://sony.github.io/model_optimization#prerequisites"><img src="https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue" /></a>
+  <a href="https://sonysemiconductorsolutions.github.io/mct-model-optimization#prerequisites"><img src="https://img.shields.io/badge/pytorch-2.3%20%7C%202.4%20%7C%202.5%20%7C%202.6-blue" /></a>
+  <a href="https://sonysemiconductorsolutions.github.io/mct-model-optimization#prerequisites"><img src="https://img.shields.io/badge/tensorflow-2.14%20%7C%202.15-blue" /></a>
+  <a href="https://sonysemiconductorsolutions.github.io/mct-model-optimization#prerequisites"><img src="https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue" /></a>
   <a href="https://github.com/sony/model_optimization/releases"><img src="https://img.shields.io/github/v/release/sony/model_optimization" /></a>
   <a href="https://github.com/sony/model_optimization/blob/main/LICENSE.md"><img src="https://img.shields.io/badge/license-Apache%202.0-blue" /></a>
 
@@ -50,9 +50,9 @@ MCT supports various quantization methods as appears below.
 
   Quantization Method  | Complexity | Computational Cost | API | Tutorial 
 -------------------- | -----------|--------------------|---------|--------
-PTQ (Post Training Quantization)  | Low | Low (~1-10 CPU minutes) | [PyTorch API](https://sony.github.io/model_optimization/api/api_docs/methods/pytorch_post_training_quantization.html) / [Keras API](https://sony.github.io/model_optimization/api/api_docs/methods/keras_post_training_quantization.html) | <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_post_training_quantization.ipynb"><img src="https://img.shields.io/badge/Pytorch-green"/></a> <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/keras/example_keras_post-training_quantization.ipynb"><img src="https://img.shields.io/badge/Keras-green"/></a>
-GPTQ (parameters fine-tuning using gradients)  | Moderate | Moderate (~1-3 GPU hours) | [PyTorch API](https://sony.github.io/model_optimization/api/api_docs/methods/pytorch_gradient_post_training_quantization.html) / [Keras API](https://sony.github.io/model_optimization/api/api_docs/methods/keras_gradient_post_training_quantization.html) | <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_mobilenet_gptq.ipynb"><img src="https://img.shields.io/badge/PyTorch-green"/></a> <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/keras/example_keras_mobilenet_gptq.ipynb"><img src="https://img.shields.io/badge/Keras-green"/></a> 
-QAT (Quantization Aware Training)  | High | High (~12-36 GPU hours) | [QAT API](https://sony.github.io/model_optimization/api/api_docs/index.html#qat) | <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/keras/example_keras_qat.ipynb"><img src="https://img.shields.io/badge/Keras-green"/></a>
+PTQ (Post Training Quantization)  | Low | Low (~1-10 CPU minutes) | [PyTorch API](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/methods/pytorch_post_training_quantization.html) / [Keras API](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/methods/keras_post_training_quantization.html) | <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_post_training_quantization.ipynb"><img src="https://img.shields.io/badge/Pytorch-green"/></a> <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/keras/example_keras_post-training_quantization.ipynb"><img src="https://img.shields.io/badge/Keras-green"/></a>
+GPTQ (parameters fine-tuning using gradients)  | Moderate | Moderate (~1-3 GPU hours) | [PyTorch API](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/methods/pytorch_gradient_post_training_quantization.html) / [Keras API](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/methods/keras_gradient_post_training_quantization.html) | <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_mobilenet_gptq.ipynb"><img src="https://img.shields.io/badge/PyTorch-green"/></a> <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/keras/example_keras_mobilenet_gptq.ipynb"><img src="https://img.shields.io/badge/Keras-green"/></a> 
+QAT (Quantization Aware Training)  | High | High (~12-36 GPU hours) | [QAT API](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/index.html#qat) | <a href="https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/keras/example_keras_qat.ipynb"><img src="https://img.shields.io/badge/Keras-green"/></a>
 
 </p>    
 </div>
@@ -95,31 +95,34 @@ Generates synthetic images based on the statistics stored in the model's batch n
 The specifications of the method are detailed in the paper: _"**Data Generation for Hardware-Friendly Post-Training Quantization**"_ [5].
 __________________________________________________________________________________________________________
 ### Structured Pruning [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_pruning_mnist.ipynb)
-Reduces model size/complexity and ensures better channels utilization by removing redundant input channels from layers and reconstruction of layer weights. Read more ([Pytorch API](https://sony.github.io/model_optimization/api/api_docs/methods/pytorch_pruning_experimental.html) / [Keras API](https://sony.github.io/model_optimization/api/api_docs/methods/keras_pruning_experimental.html)).
+Reduces model size/complexity and ensures better channels utilization by removing redundant input channels from layers and reconstruction of layer weights. Read more ([Pytorch API](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/methods/pytorch_pruning_experimental.html) / [Keras API](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/methods/keras_pruning_experimental.html)).
 __________________________________________________________________________________________________________
 ### **Debugging and Visualization**
 **🎛️ Network Editor (Modify Quantization Configurations)** [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/keras/example_keras_network_editor.ipynb). 
 Modify your model's quantization configuration for specific layers or apply a custom edit rule (e.g adjust layer's bit-width) using MCT’s network editor.
 
-**🖥️ Visualization**. Observe useful information for troubleshooting the quantized model's performance using TensorBoard. [Read more](https://sony.github.io/model_optimization/guidelines/visualization.html).
+**🖥️ Visualization**. Observe useful information for troubleshooting the quantized model's performance using TensorBoard. [Read more](https://sonysemiconductorsolutions.github.io/mct-model-optimization/guidelines/visualization.html).
 
 **🔑 XQuant (Explainable Quantization)** [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_xquant.ipynb). Get valuable insights regarding the quality and success of the quantization process of your model. The report includes histograms and similarity metrics between the original float model and the quantized model in key points of the model. The report can be visualized using TensorBoard.
+
+**🔑 XQuant Extension Tool.** Calculates the error for each layer by comparing the float model and quantized model, using both models along with the quantization log. The results are presented in reports. It identifies the causes of the detected errors and recommends appropriate improvement measures for each cause. [Read more](docs/guidelines/XQuant_Extension_Tool.html) [Troubleshoot Manual](docs/docs_troubleshoot/index.html)
+
 __________________________________________________________________________________________________________
 ### Enhanced Post-Training Quantization (EPTQ)
 As part of the GPTQ capability, we provide an advanced optimization algorithm called EPTQ.
 The specifications of the algorithm are detailed in the paper: _"**EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization**"_ [4].
 More details on how to use EPTQ via MCT can be found in the [GPTQ guidelines](https://github.com/sony/model_optimization/blob/main/model_compression_toolkit/gptq/README.md).
 
 ## <div align="center">Resources</div>
-* [User Guide](https://sony.github.io/model_optimization/index.html)  contains detailed information about MCT and guides you from installation through optimizing models for your edge AI applications.
+* [User Guide](https://sonysemiconductorsolutions.github.io/mct-model-optimization/index.html)  contains detailed information about MCT and guides you from installation through optimizing models for your edge AI applications.
 
-* MCT's [API Docs](https://sony.github.io/model_optimization/api/api_docs/) is separated per quantization methods:  
+* MCT's [API Docs](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/) is separated per quantization methods:  
 
-  * [Post-training quantization](https://sony.github.io/model_optimization/api/api_docs/index.html#ptq) | PTQ API docs
-  * [Gradient-based post-training quantization](https://sony.github.io/model_optimization/api/api_docs/index.html#gptq) | GPTQ API docs
-  * [Quantization-aware training](https://sony.github.io/model_optimization/api/api_docs/index.html#qat) | QAT API docs
+  * [Post-training quantization](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/index.html#ptq) | PTQ API docs
+  * [Gradient-based post-training quantization](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/index.html#gptq) | GPTQ API docs
+  * [Quantization-aware training](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/index.html#qat) | QAT API docs
 
-* [Debug](https://sony.github.io/model_optimization/guidelines/visualization.html) – modify optimization process or generate an explainable report
+* [Debug](https://sonysemiconductorsolutions.github.io/mct-model-optimization/guidelines/visualization.html) – modify optimization process or generate an explainable report
 
 * [Release notes](https://github.com/sony/model_optimization/releases)
 

docs/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
-# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 0ea336ad60b6f25f2eb2c0bcb6e36019
+# This file records the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: 0acc28ca46f6cf8e16b36376430fc6b8
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/_sources/api/api_docs/classes/XQuantConfig.rst.txt

@@ -9,5 +9,14 @@ XQuant Configuration
 .. autoclass:: model_compression_toolkit.xquant.common.xquant_config.XQuantConfig
     :members:
 
+.. note::
 
+    The following parameters are only used in the **xquant_report_troubleshoot_pytorch_experimental** function.
 
+    - quantize_reported_dir
+    - threshold_quantize_error 
+    - is_detect_under_threshold_quantize_error
+    - threshold_degrade_layer_ratio
+    - threshold_zscore_outlier_removal
+    - threshold_ratio_unbalanced_concatenation
+    - threshold_bitwidth_mixed_precision_with_model_output_loss_objective

docs/_sources/api/api_docs/index.rst.txt

@@ -79,6 +79,7 @@ xquant
 ===========
 
 - :ref:`xquant_report_pytorch_experimental<ug-xquant_report_pytorch_experimental>`: A function to generate an explainable quantization report for a quantized Pytorch model (experimental).
+- :ref:`xquant_report_troubleshoot_pytorch_experimental<ug-xquant_report_troubleshoot_pytorch_experimental>`: A function to generate an explainable quantization report, detect degraded layaers and judge degrade causes for a quantized Pytorch model. (experimental).
 - :ref:`xquant_report_keras_experimental<ug-xquant_report_keras_experimental>`: A function to generate an explainable quantization report for a quantized Keras model (experimental).
 
 - :ref:`XQuantConfig<ug-XQuantConfig>`: Configuration for the XQuant report (experimental).

docs/_sources/api/api_docs/methods/xquant_report_troubleshoot_pytorch_experimental.rst.txt

@@ -0,0 +1,14 @@
+:orphan:
+
+.. _ug-xquant_report_troubleshoot_pytorch_experimental:
+
+
+================================================
+XQuant Report Troubleshoot Pytorch
+================================================
+
+.. autofunction:: model_compression_toolkit.xquant.pytorch.facade_xquant_report.xquant_report_troubleshoot_pytorch_experimental
+
+
+
+