Tutorials

This collection of Python tutorials are written for running on Jupyter notebooks. The tutorials provide an introduction to the OpenVINO™ toolkit and explain how to use the Python API and tools for optimized deep learning inference. You can run the code one section at a time to see how to integrate your application with OpenVINO libraries.

Notebooks with a Binder button button can be run without installing anything. Once you have found the tutorial of your interest, just click the button next to the name of it and Binder will start it in a new tab of a browser. Binder is a free online service with limited resources (for more information about it, see the Additional Resources section).

Note

For the best performance, more control and resources, you should run the notebooks locally. Follow the Installation Guide in order to get information on how to run and manage the notebooks on your machine.


Contents:


Getting Started

The Jupyter notebooks are categorized into four classes, select one related to your needs or give them all a try. Good Luck!

First steps with OpenVINO

Brief tutorials that demonstrate how to use Python API for inference in OpenVINO.

Notebook

Description

Preview

001-hello-world
n001

Classify an image with OpenVINO.

n001-img1

002-openvino-api
n002

Learn the OpenVINO Python API.

n002-img1

003-hello-segmentation
n003

Semantic segmentation with OpenVINO.

n003-img1

004-hello-detection
n004

Text detection with OpenVINO.

n004-img1

Convert & Optimize

Tutorials that explain how to optimize and quantize models with OpenVINO tools.

Notebook

Description

Preview

101-tensorflow-to-openvino
n101

Convert TensorFlow models to OpenVINO IR.

n101-img1

102-pytorch-onnx-to-openvino

Convert PyTorch models to OpenVINO IR.

n102-img1

103-paddle-onnx-to-openvino
n103

Convert PaddlePaddle models to OpenVINO IR.

n103-img1

104-model-tools
n104

Download, convert and benchmark models from Open Model Zoo.

n104-img1

Model Demos

Demos that demonstrate inference on a particular model.

Notebook

Description

Preview

210-ct-scan-live-inference
n210

Show live inference on segmentation of CT-scan data.

n210-img1

211-speech-to-text
n211

Run inference on speech-to-text recognition model.

n211-img1

208-optical-character-recognition

Annotate text on images using text recognition resnet.

n208-img1

209-handwritten-ocr
n209

OCR for handwritten simplified Chinese and Japanese.

n209-img1
的人不一了是他有为在责新中任自之我们

218-vehicle-detection-and-recognition

Use pre-trained models to detect and recognize vehicles and their attributes with OpenVINO.

n218-img1

Model Training

Tutorials that include code to train neural networks.

Notebook

Description

Preview

301-tensorflow-training-openvino

Train a flower classification model from TensorFlow, then convert to OpenVINO IR.

n301-img1

301-tensorflow-training-openvino-pot

Use Post-training Optimization Tool (POT) to quantize the flowers model.

302-pytorch-quantization-aware-training

Use Neural Network Compression Framework (NNCF) to quantize PyTorch model.

305-tensorflow-quantization-aware-training

Use Neural Network Compression Framework (NNCF) to quantize TensorFlow model.

Live Demos

Live inference demos that run on a webcam or video files.

Notebook

Description

Preview

401-object-detection-webcam
n401

Object detection with a webcam or video file.

n401-img1

402-pose-estimation-webcam
n402

Human pose estimation with a webcam or video file.

n402-img1

403-action-recognition-webcam
n403

Human action recognition with a webcam or video file.

n403-img1

405-paddle-ocr-webcam
n405

OCR with a webcam or video file

n405-img1