senior-computer-vision

Build production-grade computer vision systems for detection and segmentation.

9|2|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/hongmaple0820/agent-academy --skill senior-computer-vision-hongmaple0820
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: senior-computer-vision
Source: https://github.com/hongmaple0820/agent-academy/tree/main/skills/others/engineering-team/senior-computer-vision
Command: npx skills add https://github.com/hongmaple0820/agent-academy --skill senior-computer-vision-hongmaple0820

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, numpy, onnx, onnxruntime, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Build production-grade computer vision capabilities by combining CNN and Vision Transformer architectures with end-to-end deployment workflows across detection and segmentation tasks.

Core Features & Use Cases

  • Architecture coverage: Object detection, instance and semantic segmentation, and multi-task CV pipelines using CNNs and Vision Transformers.
  • Production deployment: Model export, optimization, and deployment using ONNX, TensorRT, OpenVINO, CoreML, and related runtimes.
  • Automation & tooling: Automation scripts and reference configurations to streamline integration with Ultralytics, Detectron2, and MMDetection frameworks.

Quick Start

Bootstrap a production CV pipeline by selecting an architecture and exporting a deployment-ready model.

Frequently Asked Questions about senior-computer-vision

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

FAQPage Schema
How do I export object detection models to ONNX for production deployment?

Yes, you can integrate multiple computer vision frameworks like Ultralytics, Detectron2, and MMDetection. The skill provides reference configurations and automation tooling to streamline framework integration for object detection and segmentation pipelines.

Does this skill support both instance and semantic segmentation tasks?

Yes, this skill supports both instance and semantic segmentation tasks. It builds production-grade computer vision pipelines using CNN and Vision Transformer architectures, covering multi-task CV workflows end-to-end.

What's the best way to optimize computer vision models for edge environments?

The best way to optimize computer vision models for edge environments is through model export and optimization workflows. This skill applies ONNX and TensorRT configurations to deploy detection and segmentation models efficiently on edge devices.

Can I use PyTorch and ONNX runtime together for computer vision deployment?

Yes, you can use PyTorch and ONNX runtime together. The skill lists torch and onnxruntime as dependencies, enabling model training in PyTorch and subsequent export to ONNX for cross-platform deployment.

How do I build a multi-task computer vision pipeline with CNN and Vision Transformer architectures?

Build a multi-task computer vision pipeline by selecting CNN or Vision Transformer architectures for detection and segmentation. The skill provides automation scripts to bootstrap and configure production-ready CV systems with these architectures.