Nano How-to Guides

Note

This page is still a work in progress. We are adding more guides.

In Nano How-to Guides, you could expect to find multiple task-oriented, bite-sized, and executable examples. These examples will show you various tasks that BigDL-Nano could help you accomplish smoothly.

Preprocessing Optimization

PyTorch

• How to accelerate a computer vision data processing pipeline

Training Optimization

PyTorch Lightning

• How to accelerate a PyTorch Lightning application on training workloads through Intel® Extension for PyTorch*

• How to accelerate a PyTorch Lightning application on training workloads through multiple instances

• How to use the channels last memory format in your PyTorch Lightning application for training

• How to conduct BFloat16 Mixed Precision training in your PyTorch Lightning application

PyTorch

• How to convert your PyTorch training loop to use TorchNano for acceleration

• How to accelerate your PyTorch training loop with @nano decorator

• How to accelerate a PyTorch application on training workloads through Intel® Extension for PyTorch*

• How to accelerate a PyTorch application on training workloads through multiple instances

• How to use the channels last memory format in your PyTorch application for training

• How to conduct BFloat16 Mixed Precision training in your PyTorch application

TensorFlow

• How to accelerate a TensorFlow Keras application on training workloads through multiple instances

• How to optimize your model with a sparse Embedding layer and SparseAdam optimizer

• How to conduct BFloat16 Mixed Precision training in your TensorFlow Keras application

General

• How to choose the number of processes for multi-instance training

Inference Optimization

OpenVINO

• How to run inference on OpenVINO model

• How to run asynchronous inference on OpenVINO model

• How to accelerate a PyTorch / TensorFlow inference pipeline on Intel GPUs through OpenVINO

PyTorch

• How to find accelerated method with minimal latency using InferenceOptimizer

• How to accelerate a PyTorch inference pipeline through ONNXRuntime

• How to accelerate a PyTorch inference pipeline through OpenVINO

• How to accelerate a PyTorch inference pipeline through JIT/IPEX

• How to quantize your PyTorch model in INT8 for inference using Intel Neural Compressor

• How to quantize your PyTorch model in INT8 for inference using OpenVINO Post-training Optimization Tools

• How to enable automatic context management for PyTorch inference on Nano optimized models

• How to save and load optimized ONNXRuntime model

• How to save and load optimized OpenVINO model

• How to save and load optimized JIT model

• How to save and load optimized IPEX model

• How to accelerate a PyTorch inference pipeline through multiple instances

TensorFlow

• How to accelerate a TensorFlow inference pipeline through ONNXRuntime

• How to accelerate a TensorFlow inference pipeline through OpenVINO

• How to conduct BFloat16 Mixed Precision inference in a TensorFlow Keras application

• How to save and load optimized ONNXRuntime model in TensorFlow

• How to save and load optimized OpenVINO model in TensorFlow

• How to quantize your Tensorflow model for inference using Intel Neural Compressor

• How to quantize your Tensorflow model for inference using Accelerator

• How to quantize your Tensorflow model for inference by specifying accuracy control

• How to find accelerated method with minimal latency for TensorFlow model using InferenceOptimizer

Install

• How to install BigDL-Nano in Google Colab

• How to install BigDL-Nano on Windows