skills.rest
SJTU-IPADS
SJTU-IPADSOFFICIAL
Explore all skills by this author →
WebsiteGitHub

senior-computer-vision

Design, train, optimize, and deploy computer vision systems with detection, segmentation, and transformer models.

7|2|Updated Apr 13, 2026
Search Tags:#production-deployment#object-detection#computer-vision#image-segmentation#vision-transformers#onnx-tensorrt
One-click install
npx skills add https://github.com/SJTU-IPADS/SkVM-data --skill senior-computer-vision-sjtu-ipads
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: senior-computer-vision
Source: https://github.com/SJTU-IPADS/SkVM-data/tree/main/skills/senior-computer-vision
Command: npx skills add https://github.com/SJTU-IPADS/SkVM-data --skill senior-computer-vision-sjtu-ipads

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Guides engineers to design, train, optimize, and deploy computer vision systems that integrate detection, segmentation, and transformer architectures across production workflows.

Core Features & Use Cases

  • Object detection, instance and semantic segmentation, and vision transformer models.
  • Production deployment with ONNX/TensorRT, PyTorch ecosystem, and frameworks like Ultralytics, Detectron2, MMDetection.
  • Workflow templates for data preparation, model training, optimization, and deployment in cloud, edge, and embedded contexts.

Quick Start

Follow the steps to set up a production-grade CV project from data preparation to model deployment.

Frequently Asked Questions about senior-computer-vision

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

FAQPage Schema
How do I deploy a computer vision model using ONNX and TensorRT?▼

To deploy a computer vision model using ONNX and TensorRT, you export the trained PyTorch architecture to ONNX, then optimize and run it via TensorRT for high-speed inference across cloud, edge, and embedded devices.

What is the best way to build a pipeline for object detection and image segmentation?▼

Building a pipeline for object detection and image segmentation involves combining frameworks like Detectron2 or MMDetection with PyTorch to handle data preparation, model training, and optimization for production-grade deployment.

Can I train and deploy vision transformers for edge devices?▼

Yes, you can train and deploy vision transformers for edge devices by building the models in PyTorch, then optimizing and converting them using ONNX, TensorRT, OpenVINO, or CoreML ecosystems to fit embedded constraints.

How do I prepare data and train computer vision models for production deployment?▼

Preparing data and training computer vision models for production deployment requires utilizing workflow templates that structure data preparation, training, and optimization to ensure models are ready for cloud, edge, and embedded contexts.

Does this computer vision pipeline work with OpenVINO and CoreML ecosystems?▼

Yes, this computer vision pipeline works with OpenVINO and CoreML ecosystems, allowing you to optimize and deploy trained object detection, segmentation, and vision transformer models across different hardware platforms.

Related Skills

Explore More Software Engineering Skills→
HopeArtOrgHopeArtOrg
8

onnx-export

Convert JAX/Python ML models to ONNX format via Google Colab notebooks.

Official
Intermediate
pytorchpytorch
4.9k

export

Convert PyTorch models to .pte format for ExecuTorch deployment.

Official
Advanced
4lerman4lerman

senior-computer-vision

Design, train, and deploy computer vision models with PyTorch and ONNX.

Community
Advanced
NVIDIANVIDIA
13.2k

trt-torch-quickstart

Convert PyTorch models to TensorRT engines using torch_tensorrt.

Official
Intermediate