开源软件名称：

开源软件地址：

开源软件介绍：

Neural Network Compression Framework (NNCF)

NNCF provides a suite of advanced algorithms for Neural Networks inference optimization in OpenVINO™ with minimal accuracy drop.

NNCF is designed to work with models from PyTorch and TensorFlow.

NNCF provides samples that demonstrate the usage of compression algorithms for three different use cases on public PyTorch andTensorFlow models and datasets: Image Classification, Object Detection and Semantic Segmentation.Compression results achievable with the NNCF-powered samples can be found in a table atthe end of this document.

The framework is organized as a Python* package that can be built and used in a standalone mode. The frameworkarchitecture is unified to make it easy to add different compression algorithms for both PyTorch and TensorFlow deeplearning frameworks.

Key Features

• Support of various compression algorithms, applied during a model fine-tuning process to achieve a better performance-accuracy trade-off:

  Compression algorithm	PyTorch	TensorFlow
  Quantization	Supported	Supported
  Mixed-Precision Quantization	Supported	Not supported
  Binarization	Supported	Not supported
  Sparsity	Supported	Supported
  Filter pruning	Supported	Supported

• Automatic, configurable model graph transformation to obtain the compressed model.

  NOTE: Limited support for TensorFlow models. The models created using Sequential or Keras Functional API are only supported.

• Common interface for compression methods.

• GPU-accelerated layers for faster compressed model fine-tuning.

• Distributed training support.

• Configuration file examples for each supported compression algorithm.

• Git patches for prominent third-party repositories (huggingface-transformers) demonstrating the process of integrating NNCF into custom training pipelines

• Exporting PyTorch compressed models to ONNX* checkpoints and TensorFlow compressed models to SavedModel or Frozen Graph format, ready to use with OpenVINO™ toolkit.

• Support for Accuracy-Aware model training pipelines via the Adaptive Compression Level Training and Early Exit Training.

Usage

The NNCF is organized as a regular Python package that can be imported in your target training pipeline script.The basic workflow is loading a JSON configuration script containing NNCF-specific parameters determining the compression to be applied to your model, and then passing your model along with the configuration script to the create_compressed_model function.This function returns a model with additional modifications necessary to enable algorithm-specific compression during fine-tuning and handle to the object allowing you to control the compression during the training process:

Usage example with PyTorch

import torchimport nncf  # Important - should be imported directly after torchfrom nncf import NNCFConfigfrom nncf.torch import create_compressed_model, register_default_init_args# Instantiate your uncompressed modelfrom torchvision.models.resnet import resnet50model = resnet50()# Load a configuration file to specify compressionnncf_config = NNCFConfig.from_json("resnet50_int8.json")# Provide data loaders for compression algorithm initialization, if necessaryimport torchvision.datasets as datasetsrepresentative_dataset = datasets.ImageFolder("/path")init_loader = torch.utils.data.DataLoader(representative_dataset)nncf_config = register_default_init_args(nncf_config, init_loader)# Apply the specified compression algorithms to the modelcompression_ctrl, compressed_model = create_compressed_model(model, nncf_config)# Now use compressed_model as a usual torch.nn.Module # to fine-tune compression parameters along with the model weights# ... the rest of the usual PyTorch-powered training pipeline# Export to ONNX or .pth when done fine-tuningcompression_ctrl.export_model("compressed_model.onnx")torch.save(compressed_model.state_dict(), "compressed_model.pth")

Usage example with TensorFlow

import tensorflow as tffrom nncf import NNCFConfigfrom nncf.tensorflow import create_compressed_model, register_default_init_args# Instantiate your uncompressed modelfrom tensorflow.keras.applications import ResNet50model = ResNet50()# Load a configuration file to specify compressionnncf_config = NNCFConfig.from_json("resnet50_int8.json")# Provide dataset for compression algorithm initializationrepresentative_dataset = tf.data.Dataset.list_files("/path/*.jpeg")nncf_config = register_default_init_args(nncf_config, representative_dataset, batch_size=1)# Apply the specified compression algorithms to the modelcompression_ctrl, compressed_model = create_compressed_model(model, nncf_config)# Now use compressed_model as a usual Keras model# to fine-tune compression parameters along with the model weights# ... the rest of the usual TensorFlow-powered training pipeline# Export to Frozen Graph, TensorFlow SavedModel or .h5  when done fine-tuning compression_ctrl.export_model("compressed_model.pb", save_format='frozen_graph')

For a more detailed description of NNCF usage in your training code, see this tutorial.For in-depth examples of NNCF integration, browse the sample scripts code, or the example patches to third-party repositories.

Model Compression Samples

For a quicker start with NNCF-powered compression, you can also try the sample scripts, each of which provides a basic training pipeline for classification, semantic segmentation and object detection neural network training correspondingly.

To run the samples please refer to the corresponding tutorials:

• PyTorch samples:
  • Image Classification sample
  • Object Detection sample
  • Semantic Segmentation sample
• TensorFlow samples:
  • Image Classification sample
  • Object Detection sample
  • Instance Segmentation sample

Model Compression Notebooks

A collection of ready-to-run Jupyter* notebooks are also available to demonstrate how to use NNCF compression algorithmsto optimize models for inference with the OpenVINO Toolkit.

• Optimizing PyTorch models with NNCF of OpenVINO by 8-bit quantization
• Optimizing TensorFlow models with NNCF of OpenVINO by 8-bit quantization
• Post-Training Quantization of Pytorch model with NNCF

Third-party repository integration

NNCF may be straightforwardly integrated into training/evaluation pipelines of third-party repositories.

Used by

• OpenVINO Training Extensions

  NNCF is integrated into OpenVINO Training Extensions as model optimization backend. So you can train, optimize and export new models based on the available model templates as well as run exported models with OpenVINO.

Git patches for third-party repository

See third_party_integration for examples of code modifications (Git patches and base commit IDs are provided) that are necessary to integrate NNCF into the following repositories:

• huggingface-transformers

System requirements

• Ubuntu* 18.04 or later (64-bit)
• Python* 3.6.2 or later
• Supported frameworks:
  • PyTorch* >=1.5.0, <=1.9.1 (1.8.0 not supported)
  • TensorFlow* >=2.4.0, <=2.5.3

This repository is tested on Python* 3.6.2+, PyTorch* 1.9.1 (NVidia CUDA* Toolkit 10.2) and TensorFlow* 2.5.3 (NVidia CUDA* Toolkit 11.2).

Installation

We suggest to install or use the package in the Python virtual environment.

If you want to optimize a model from PyTorch, install PyTorch by following PyTorch installation guide.If you want to optimize a model from TensorFlow, install TensorFlow by following TensorFlow installation guide.

As a package built from a checked-out repository:

Install the package and its dependencies by running the following in the repository root directory:

python setup.py install

Alternatively, If you don't install any backend you can install NNCF and PyTorch in one line with:

python setup.py install --torch

Install NNCF and TensorFlow in one line:

python setup.py install --tf

NB: For launching example scripts in this repository, we recommend replacing the install option above with develop and setting the PYTHONPATH variable to the root of the checked-out repository.

As a PyPI package:

NNCF can be installed as a regular PyPI package via pip:

pip install nncf

Alternatively, If you don't install any backend you can install NNCF and PyTorch in one line with:

pip install nncf[torch]

Install NNCF and TensorFlow in one line:

pip install nncf[tf]

NNCF is also available via conda:

conda install -c conda-forge nncf

From a specific commit hash using pip:

pip install git+https://github.com/openvinotoolkit/nncf@bd189e2#egg=nncf

Note that in order for this to work for pip versions >= 21.3, your Git version must be at least 2.22.

As a Docker image

Use one of the Dockerfiles in the docker directory to build an image with an environment already set up and ready for running NNCF sample scripts.

Contributing

Refer to the CONTRIBUTING.md file for guidelines on contributions to the NNCF repository.

NNCF Compressed Model Zoo

Results achieved using sample scripts, example patches to third-party repositories and NNCF configuration files providedwith this repository. See README.md files for sample scripts and example patchesto find instruction and links to exact configuration files and final checkpoints.

• PyTorch models
  • Classification
  • Object detection
  • Semantic segmentation
  • Natural language processing (3rd-party training pipelines)
• TensorFlow models
  • Classification
  • Object detection
  • Instance segmentation

PyTorch models

Classification

PyTorch Model	Compression algorithm	Dataset	Accuracy (Drop) %
ResNet-50	INT8	ImageNet	76.42 (-0.26)
ResNet-50	INT8 (per-tensor for weights)	ImageNet	76.37 (-0.21)
ResNet-50	Mixed, 44.8% INT8 / 55.2% INT4	ImageNet	76.2 (-0.04)
ResNet-50	INT8 + Sparsity 61% (RB)	ImageNet	75.43 (0.73)
ResNet-50	INT8 + Sparsity 50% (RB)	ImageNet	75.55 (0.61)
ResNet-50	Filter pruning, 40%, geometric median criterion	ImageNet	75.62 (0.54)
Inception V3	INT8	ImageNet	78.25 (-0.91)
Inception V3	INT8 + Sparsity 61% (RB)	ImageNet	77.58 (-0.24)
MobileNet V2	INT8	ImageNet	71.35 (0.58)
MobileNet V2	INT8 (per-tensor for weights)	ImageNet	71.3 (0.63)
MobileNet V2	Mixed, 46.6% INT8 / 53.4% INT4	ImageNet	70.92 (1.01)
MobileNet V2	INT8 + Sparsity 52% (RB)	ImageNet	71.11 (0.82)
MobileNet V3 small	INT8	ImageNet	66.94 (0.73)
SqueezeNet V1.1	INT8	ImageNet	58.28 (-0.04)
SqueezeNet V1.1	INT8 (per-tensor for weights)	ImageNet	58.26 (-0.02)
SqueezeNet V1.1	Mixed, 54.7% INT8 / 45.3% INT4	ImageNet	58.9 (-0.66)
ResNet-18	XNOR (weights), scale/threshold (activations)	ImageNet	61.63 (8.17)
ResNet-18	DoReFa (weights), scale/threshold (activations)	ImageNet	61.61 (8.19)
ResNet-18	Filter pruning, 40%, magnitude criterion	ImageNet	69.26 (0.54)
ResNet-18	Filter pruning, 40%, geometric median criterion	ImageNet	69.32 (0.48)
ResNet-34	Filter pruning, 40%, geometric median criterion	ImageNet	72.73 (0.57)
GoogLeNet	Filter pruning, 40%, geometric median criterion	ImageNet	68.82 (0.93)

Object detection

Semantic segmentation

PyTorch Model	Compression algorithm	Dataset	Accuracy (Drop) %
UNet	INT8	CamVid	71.8 (0.15)
UNet	INT8 + Sparsity 60% (Magnitude)	CamVid	72.03 (-0.08)
ICNet	INT8	CamVid	67.86 (0.03)
ICNet	INT8 + Sparsity 60% (Magnitude)	CamVid	67.18 (0.71)
UNet	INT8	Mapillary	55.87 (0.36)
UNet	INT8 + Sparsity 60% (Magnitude)	Mapillary	55.65 (0.58)
UNet	Filter pruning, 25%, geometric median criterion	Mapillary	55.62 (0.61)

NLP (HuggingFace Transformers-powered models)

PyTorch Model	Compression algorithm	Dataset	Accuracy (Drop) %
BERT-base-chinese	INT8	XNLI	77.22 (0.46)
BERT-base-cased	INT8	CoNLL2003	99.18 (-0.01)
BERT-base-cased	INT8	MRPC	84.8 (-0.24)
BERT-large (Whole Word Masking)	INT8	SQuAD v1.1	F1: 92.68 (0.53)
RoBERTa-large	INT8	MNLI	matched: 89.25 (1.35)
DistilBERT-base	INT8	SST-2	90.3 (0.8)
MobileBERT	INT8	SQuAD v1.1	F1: 89.4 (0.58)
GPT-2	INT8	WikiText-2 (raw)	perplexity: 20.9 (-1.17)

TensorFlow models

Classification

Object detection

Instance segmentation

TensorFlow Model	Compression algorithm	Dataset	mAP (drop) %
MaskRCNN	INT8 (per-tensor for weights)	COCO2017	bbox: 37.27 (0.06) segm: 33.54 (0.02)
MaskRCNN	Sparsity 50% (Magnitude)	COCO2017	bbox: 36.93 (0.40) segm: 33.23 (0.33)

Citing

@article{kozlov2020neural,    title =   {Neural network compression framework for fast model inference},    author =  {Kozlov, Alexander and Lazarevich, Ivan and Shamporov, Vasily and Lyalyushkin, Nikolay and Gorbachev, Yury},    journal = {arXiv preprint arXiv:2002.08679},    year =    {2020}}

Legal Information

[*] Other names and brands may be claimed as the property of others.