[Deprecated] Post-training Optimization Tool API Examples¶
Danger
Post-training Optimization Tool is deprecated since OpenVINO 2023.0. Neural Network Compression Framework (NNCF) is recommended for the post-training quantization instead.
The Post-training Optimization Tool contains multiple examples that demonstrate how to use its API to optimize DL models. All available examples can be found on GitHub.
The following examples demonstrate the implementation of Engine
, Metric
, and DataLoader
interfaces for various use cases:
Quantizing Image Classification model
Uses a single
MobilenetV2
model from TensorFlowImplements
DataLoader
to load .JPEG images and annotations of the Imagenet databaseImplements
Metric
interface to calculate Accuracy at top-1 metricUses DefaultQuantization algorithm for quantization model
Quantizing Object Detection Model with Accuracy Control
Uses asingle
MobileNetV1 FPN
model from TensorFlowImplements
Dataloader
to load images of the COCO databaseImplements
Metric
interface to calculatemAP@[.5:.95]
metricUses
AccuracyAwareQuantization
algorithm for quantization model
Quantizing Semantic Segmentation Model
Uses a single
DeepLabV3
model from TensorFlowImplements
DataLoader
to load .JPEG images and annotations of the Pascal VOC 2012 databaseImplements
Metric
interface to calculate Mean Intersection Over Union metricUses DefaultQuantization algorithm for quantization model
Quantizing 3D Segmentation Model
Uses a single
Brain Tumor Segmentation
model from PyTorchImplements
DataLoader
to load images in NIfTI format from the Medical Segmentation Decathlon BRATS 2017 databaseImplements
Metric
interface to calculate Dice Index metricDemonstrates how to use image metadata obtained during data loading to post-process the raw model output
Uses DefaultQuantization algorithm for quantization model
-
Uses a cascaded (composite)
MTCNN
model from Caffe that consists of three separate models in an OpenVINO™ Intermediate Representation (IR)Implements
Dataloader
to load .jpg images of the WIDER FACE databaseImplements
Metric
interface to calculate Recall metricImplements
Engine
class that is inherited fromIEEngine
to create a complex staged pipeline to sequentially execute each of the three stages of the MTCNN model, represented by multiple models in IR. It uses engine helpers to set a model in OpenVINO Inference Engine and process raw model output for the correct statistics collectionUses DefaultQuantization algorithm for quantization model
-
Uses models from Kaldi
Implements
DataLoader
to load data in .ark formatUses DefaultQuantization algorithm for quantization model
After the execution of each example above, the quantized model is placed into the folder optimized
. The accuracy validation of the quantized model is performed right after the quantization.