atc-model-converter

Official

Convert ONNX models to Ascend OM and validate end-to-end.

Authorascend-ai-coding
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Complete toolkit for converting ONNX models to Ascend OM format using ATC and validating results via AIS Bench and end-to-end inference workflows on Ascend devices.

Core Features & Use Cases

  • ATC ONNX-to-OM conversion across multiple CANN versions (8.3.RC1, 8.5.0+) with compatibility guidance.
  • End-to-end inference workflow using ais_bench to run OM models and compare against CPU ONNX outputs.
  • YOLO model deployment and multi-task inference support (detection, pose, segmentation, OBB) with post-processing guides and troubleshooting.
  • Comprehensive environment setup, batch conversion helpers, and pre/post-processing utilities to accelerate model deployment.

Quick Start

Install the required CANN toolkit and environment, then run the ATC workflow to convert an ONNX model to OM and validate it with ais_bench.

Dependency Matrix

Required Modules

onnxruntimeais_benchopencv-pythonultralyticstorchtorchvision

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: atc-model-converter
Download link: https://github.com/ascend-ai-coding/awesome-ascend-skills/archive/main.zip#atc-model-converter

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.