About this Guide

This guide provides detailed instructions for exporting PyTorch machine learning models to the ONNX format. It aims to simplify the process of converting models to ONNX for interoperability and deployment across different platforms and frameworks.

Prerequisites

Before you begin, ensure you have the following:

• Python 3.6+
• pip
• Pytorch
• Basic understanding of machine learning models and frameworks
• ONNX and latest onnxruntime
• Netron.app for visualizing and analyzing ONNX models

Installation

To get started, you'll need to install the necessary libraries. You can install the required libraries by using:

pip install -r requirements.txt

Exporting Models (Pytorch)

Classification

• AlexNet
• ConvNeXt_base
• ConvNeXt_small
• ConvNeXt_large
• DenseNet121
• DenseNet161
• DenseNet169
• DenseNet201
• EfficientNet_BO
• EfficientNet_B1
• EfficientNet_B2
• EfficientNet_B3
• EfficientNet_B4
• EfficientNet_B5
• EfficientNet_B6
• EfficientNet_B7
• EfficientNet_V2_S
• EfficientNet_V2_M
• EfficientNet_V2_L
• GoogleNet
• Inception_V3
• MNASNet0_5
• MNASNet0_75
• MNASNet1_0
• MNASNet1_3
• MaxiVit_T
• MobileNet_V2
• MobileNet_V3_S
• MobileNet_V3_L
• ResNet18
• ResNet34
• ResNet50
• ResNet101
• ResNet152
• ShuffleNet

Object Detection Models

• FasterRCNN_V1 (fasterrcnn_resnet50_fpn)
• FasterRCNN_V2 (fasterrcnn_resnet50_fpn_v2)
• FasterRCNN_V3_L (fasterrcnn_mobilenet_v3_large_fpn)
• FasterRCNN_V3_L_320 (fasterrcnn_mobilenet_v3_large_320_fpn)
• YOLOV8n
• YOLOV8s
• YOLOV8m
• YOLOV8l
• YOLOV8x

Image Segmentation Models

• UNet

Natural Language Processing

• BERT

Examples

Find practical examples in the Examples directory.

License

This project is licensed under the MIT License.