Update NNCF doc

docs/articles_en/openvino-workflow/model-optimization-guide/compressing-models-during-training.rst

@@ -16,13 +16,13 @@ accuracy and higher performance, and better results than post-training quantizat
 enables you to set the minimum acceptable accuracy value for your optimized model, determining
 the optimization efficiency.
 
-With a few lines of code, you can apply NNCF compression to a PyTorch or TensorFlow training
+With a few lines of code, you can apply NNCF compression to a PyTorch training
 script. Once the model is optimized, you may convert it to the
 :doc:`OpenVINO IR format <../../documentation/openvino-ir-format>`, getting even better
 inference results with OpenVINO Runtime. To optimize your model, you will need:
 
-* A PyTorch or TensorFlow floating-point model.
-* A training pipeline set up in the original framework (PyTorch or TensorFlow).
+* A PyTorch floating-point model.
+* A training pipeline set up in the PyTorch framework.
 * Training and validation datasets.
 * A `JSON configuration file <https://github.com/openvinotoolkit/nncf/blob/develop/docs/ConfigFile.md>`__
   specifying which compression methods to use.
@@ -45,9 +45,8 @@ quantization errors part of the overall training loss and tries to minimize thei
 
 To learn more, see:
 
-* guide on quantization for :doc:`PyTorch and TensorFlow <./compressing-models-during-training/quantization-aware-training>`.
+* guide on quantization for :doc:`PyTorch <./compressing-models-during-training/quantization-aware-training>`.
 * Jupyter notebook on `Quantization Aware Training with NNCF and PyTorch <https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/pytorch-quantization-aware-training>`__.
-* Jupyter notebook on `Quantization Aware Training with NNCF and TensorFlow <https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/tensorflow-quantization-aware-training>`__.
 
 
 Filter pruning

docs/articles_en/openvino-workflow/model-optimization-guide/compressing-models-during-training/filter-pruning.rst

@@ -46,13 +46,6 @@ In this step, NNCF-related imports are added in the beginning of the training sc
          :language: python
          :fragment: [imports]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [imports]
-
 2. Create NNCF configuration
 ++++++++++++++++++++++++++++
 
@@ -68,13 +61,6 @@ of optimization methods (`"compression"` section).
          :language: python
          :fragment: [nncf_congig]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [nncf_congig]
-
 Here is a brief description of the required parameters of the Filter Pruning method. For a full description refer to the
 `GitHub <https://github.com/openvinotoolkit/nncf/blob/develop/docs/usage/training_time_compression/other_algorithms/Pruning.md>`__ page.
 
@@ -103,13 +89,6 @@ optimization.
          :language: python
          :fragment: [wrap_model]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [wrap_model]
-
 4. Fine-tune the model
 ++++++++++++++++++++++
 
@@ -126,14 +105,6 @@ of the original model.
          :language: python
          :fragment: [tune_model]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [tune_model]
-
-
 5. Multi-GPU distributed training
 +++++++++++++++++++++++++++++++++
 
@@ -149,18 +120,11 @@ fine-tuning that will inform optimization methods to do some adjustments to func
          :language: python
          :fragment: [distributed]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [distributed]
-
 6. Export quantized model
 +++++++++++++++++++++++++
 
 When fine-tuning finishes, the quantized model can be exported to the corresponding format for further inference: ONNX in
-the case of PyTorch and frozen graph - for TensorFlow 2.
+the case of PyTorch.
 
 .. tab-set::
 
@@ -171,14 +135,6 @@ the case of PyTorch and frozen graph - for TensorFlow 2.
          :language: python
          :fragment: [export]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [export]
-
-
 These were the basic steps to applying the QAT method from the NNCF. However, it is required in some cases to save/load model
 checkpoints during the training. Since NNCF wraps the original model with its own object it provides an API for these needs.
 
@@ -197,14 +153,6 @@ To save model checkpoint use the following API:
          :language: python
          :fragment: [save_checkpoint]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [save_checkpoint]
-
-
 8. (Optional) Restore from checkpoint
 +++++++++++++++++++++++++++++++++++++
 
@@ -219,20 +167,13 @@ To restore the model from checkpoint you should use the following API:
          :language: python
          :fragment: [load_checkpoint]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/pruning_tf.py
-         :language: python
-         :fragment: [load_checkpoint]
-
 For more details, see the following `documentation <https://github.com/openvinotoolkit/nncf/blob/develop/docs/usage/training_time_compression/other_algorithms/Pruning.md>`__.
 
 Deploying pruned model
 ######################
 
 The pruned model requires an extra step that should be done to get performance improvement. This step involves removal of the
-zero filters from the model. This is done at the model conversion step using  :doc:`model conversion API <../../model-preparation>` tool when model is converted from the framework representation (ONNX, TensorFlow, etc.) to OpenVINO Intermediate Representation.
+zero filters from the model. This is done at the model conversion step using  :doc:`model conversion API <../../model-preparation>` tool when model is converted from the framework representation (ONNX, etc.) to OpenVINO Intermediate Representation.
 
 * To remove zero filters from the pruned model add the following parameter to the model conversion command: ``transform=Pruning``
 
@@ -244,6 +185,3 @@ Examples
 ####################
 
 * `PyTorch Image Classification example <https://github.com/openvinotoolkit/nncf/blob/develop/examples/torch/classification>`__
-
-* `TensorFlow Image Classification example <https://github.com/openvinotoolkit/nncf/tree/develop/examples/tensorflow/classification>`__
-

docs/articles_en/openvino-workflow/model-optimization-guide/compressing-models-during-training/quantization-aware-training.rst

@@ -12,11 +12,6 @@ knowledgeable in Python programming and familiar with the training code for the
 
 Steps required to apply QAT to the model:
 
-.. note::
-   Currently, NNCF for TensorFlow supports the optimization of models created using the Keras
-   `Sequential API <https://www.tensorflow.org/guide/keras/sequential_model>`__ or
-   `Functional API <https://www.tensorflow.org/guide/keras/functional>`__.
-
 1. Apply Post Training Quantization to the Model
 #################################################
 
@@ -31,13 +26,6 @@ Quantize the model using the :doc:`Post-Training Quantization <../quantizing-mod
          :language: python
          :fragment: [quantize]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/qat_tf.py
-         :language: python
-         :fragment: [quantize]
-
 2. Fine-tune the Model
 #######################
 
@@ -56,13 +44,6 @@ forward and backward passes.
          :language: python
          :fragment: [tune_model]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/qat_tf.py
-         :language: python
-         :fragment: [tune_model]
-
 .. note::
    The precision of weight transitions to INT8 only after converting the model to OpenVINO
    Intermediate Representation. You can expect a reduction in the model footprint only for
@@ -85,13 +66,6 @@ To save a model checkpoint, use the following API:
          :language: python
          :fragment: [save_checkpoint]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/qat_tf.py
-         :language: python
-         :fragment: [save_checkpoint]
-
 4. (Optional) Restore from Checkpoint
 ######################################
 
@@ -106,13 +80,6 @@ To restore the model from checkpoint, use the following API:
          :language: python
          :fragment: [load_checkpoint]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/code/qat_tf.py
-         :language: python
-         :fragment: [load_checkpoint]
-
 Deploying the Quantized Model
 ##############################
 
@@ -128,18 +95,10 @@ any additional steps.
          :language: python
          :fragment:  [inference]
 
-   .. tab-item:: TensorFlow 2
-      :sync: tensorflow-2
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/ptq/code/ptq_tensorflow.py
-         :language: python
-         :fragment:  [inference]
-
 For more details, see the corresponding :doc:`documentation <../../running-inference>`.
 
 Examples
 #########
 
 * `Quantization-aware Training of Resnet18 PyTorch Model <https://github.com/openvinotoolkit/nncf/tree/develop/examples/quantization_aware_training/torch/resnet18>`__
 * `Quantization-aware Training of STFPM PyTorch Model <https://github.com/openvinotoolkit/nncf/tree/develop/examples/quantization_aware_training/torch/anomalib>`__
-* `Quantization-aware Training of MobileNet v2 TensorFlow Model <https://github.com/openvinotoolkit/nncf/tree/develop/examples/quantization_aware_training/tensorflow/mobilenet_v2>`__

docs/articles_en/openvino-workflow/model-optimization-guide/quantizing-models-post-training.rst

@@ -25,7 +25,7 @@ flows:
 
 .. note
 
-   NNCF offers a Python API, for compressing PyTorch, TensorFlow 2.x, ONNX, and OpenVINO IR
+   NNCF offers a Python API, for compressing PyTorch, ONNX, and OpenVINO IR
    model formats. OpenVINO IR offers the most comprehensive support.
 
 

docs/articles_en/openvino-workflow/model-optimization-guide/quantizing-models-post-training/basic-quantization-flow.rst

@@ -5,7 +5,7 @@ Basic Quantization Flow
 Introduction
 ####################
 
-The basic quantization flow is the simplest way to apply 8-bit quantization to the model. It is available for models in the following frameworks: OpenVINO, PyTorch, TensorFlow 2.x, and ONNX. The basic quantization flow is based on the following steps:
+The basic quantization flow is the simplest way to apply 8-bit quantization to the model. It is available for models in the following frameworks: OpenVINO, PyTorch, and ONNX. The basic quantization flow is based on the following steps:
 
 * Set up an environment and install dependencies.
 * Prepare a representative **calibration dataset** that is used to estimate quantization parameters of the activations within the model, for example, of 300 samples.
@@ -56,13 +56,6 @@ The transformation function is a function that takes a sample from the dataset a
          :language: python
          :fragment: [dataset]
 
-   .. tab-item:: TensorFlow
-      :sync: tensorflow
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/ptq/code/ptq_tensorflow.py
-         :language: python
-         :fragment: [dataset]
-
    .. tab-item:: TorchFX
       :sync: torch_fx
 
@@ -102,13 +95,6 @@ See the `example section <#examples-of-how-to-apply-nncf-post-training-quantizat
          :language: python
          :fragment: [quantization]
 
-   .. tab-item:: TensorFlow
-      :sync: tensorflow
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/ptq/code/ptq_tensorflow.py
-         :language: python
-         :fragment: [quantization]
-
    .. tab-item:: TorchFX
       :sync: torch_fx
 
@@ -142,13 +128,6 @@ If you have not already installed OpenVINO developer tools, install it with ``pi
          :language: python
          :fragment:  [inference]
 
-   .. tab-item:: TensorFlow
-      :sync: tensorflow
-
-      .. doxygensnippet:: docs/optimization_guide/nncf/ptq/code/ptq_tensorflow.py
-         :language: python
-         :fragment:  [inference]
-
 TorchFX models can utilize OpenVINO optimizations using `torch.compile(..., backend="openvino") <https://docs.openvino.ai/2025/openvino-workflow/torch-compile.html>`__ functionality:
 
 .. tab-set::
@@ -242,5 +221,4 @@ Examples of how to apply NNCF post-training quantization:
 * `Post-Training Quantization of MobileNet v2 PyTorch Model <https://github.com/openvinotoolkit/nncf/blob/develop/examples/post_training_quantization/torch/mobilenet_v2>`__
 * `Post-Training Quantization of SSD PyTorch Model <https://github.com/openvinotoolkit/nncf/blob/develop/examples/post_training_quantization/torch/ssd300_vgg16>`__
 * `Post-Training Quantization of MobileNet v2 ONNX Model <https://github.com/openvinotoolkit/nncf/blob/develop/examples/post_training_quantization/onnx/mobilenet_v2>`__
-* `Post-Training Quantization of MobileNet v2 TensorFlow Model <https://github.com/openvinotoolkit/nncf/blob/develop/examples/post_training_quantization/tensorflow/mobilenet_v2>`__