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.
Tutorials showing this logo may be run remotely using Binder with no setup, although running the notebooks on a local system is recommended for best performance. See the OpenVINO™ Notebooks Installation Guide to install and run locally.
Getting Started¶
Convert & Optimize¶
- Convert a TensorFlow Model to OpenVINO
- Convert a PyTorch Model to ONNX and OpenVINO IR
- Convert a PaddlePaddle Model to ONNX and OpenVINO IR
- Working with Open Model Zoo Models
- Quantize NLP models with OpenVINO Post-Training Optimization Tool
- Automatic Device Selection with OpenVINO™
- Quantize a Segmentation Model and Show Live Inference
- Object Detection Quantization
- Post-Training Quantization of PyTorch models with NNCF
- Quantization of Image Classification Models
- INT8 Quantization with Post-training Optimization Tool (POT) in Simplified Mode tutorial
Model Demos¶
- Monodepth Estimation with OpenVINO
- Single Image Super Resolution with OpenVINO
- Video Super Resolution with OpenVINO
- Image Background Removal with U^2-Net and OpenVINO
- Photos to Anime with PaddleGAN and OpenVINO
- Super Resolution with PaddleGAN and OpenVINO
- Optical Character Recognition (OCR) with OpenVINO
- Handwritten Chinese and Japanese OCR
- Live Inference and Benchmark CT-scan Data with OpenVINO
- Speech to Text with OpenVINO
- Style Transfer on ONNX Models with OpenVINO
- Interactive question answering with OpenVINO
- PaddlePaddle Image Classification with OpenVINO
- Image In-painting with OpenVINO™
- Deblur Photos with DeblurGAN-v2 and OpenVINO
- Vehicle Detection And Recognition with OpenVINO
- Imports
- Download Models
- Load Models
- Use detection model to detect vehicles