skills.rest
ascend-ai-coding
ascend-ai-codingOFFICIAL
Explore all skills by this author →
GitHub

atc-model-converter

Convert ONNX models to Ascend OM format with ATC and validate via AIS Bench.

156|53|Updated Feb 14, 2026
Search Tags:#inference#onnx#model-conversion#yolo#ascend#atc#om
One-click install
npx skills add https://github.com/ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: atc-model-converter
Source: https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/atc-model-converter
Command: npx skills add https://github.com/ascend-ai-coding/awesome-ascend-skills --skill atc-model-converter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires onnxruntime, ais_bench, opencv-python, ultralytics, torch, torchvision, and includes scripts (resource) and references (resource) components.

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.

Frequently Asked Questions about atc-model-converter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert ONNX models to Ascend OM format using ATC?▼

To convert ONNX models to Ascend OM format, run the ATC workflow included here, which requires a compatible CANN toolkit and Python ecosystem to execute the conversion process.

Can I validate ONNX to OM conversion accuracy with AIS Bench?▼

Yes, you can validate conversion accuracy by running end-to-end AIS Bench inference to execute the OM model and directly compare its outputs against the original CPU ONNX results.

Does the ONNX to OM conversion workflow support YOLO models?▼

Yes, the ONNX to OM conversion workflow supports YOLO model deployment across multiple tasks including detection, pose, segmentation, and OBB, complete with post-processing guides.

What CANN versions are supported for Ascend OM model conversion?▼

The ATC ONNX-to-OM conversion workflow supports multiple CANN versions, specifically providing compatibility guidance for 8.3.RC1 and 8.5.0+ environments.

What Python environment do I need for ATC model conversion and AIS Bench validation?▼

You need a Python ecosystem version between 3.7 and 3.10, along with installed dependencies like ais_bench, onnxruntime, and a matching CANN or Opp setup for ATC model conversion.

Related Skills

Explore More Software Engineering Skills→
AscendAscend
31

atc-model-converter

A structured approach to managing your finances and hitting your savings targets through automated transfers.

Official
Advanced
zenobi-uszenobi-us
68

machine-learning-engineer

Deploy scalable ML models with real-time inference, monitoring, and CI/CD pipelines.

Official
Advanced
nimeshgurungnimeshgurung

senior-computer-vision

Builds computer vision systems for image/video processing, object detection, and deployment using PyTorch, OpenCV, and YOLO.

Community
Advanced
adaptyvbioadaptyvbio
151

boltz

Predict protein complex structures with Boltz-1/Boltz-2 and output CIF models.

Official
Advanced