skills.rest
Patasse97
Patasse97COMMUNITY
Explore all skills by this author →
GitHub

senior-computer-vision

Automate computer vision workflows from dataset preparation to model deployment.

Updated Apr 9, 2026
Search Tags:#deployment#production#pipelines#segmentation#object-detection#computer-vision
One-click install
npx skills add https://github.com/Patasse97/claude-skills --skill senior-computer-vision-patasse97
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: senior-computer-vision
Source: https://github.com/Patasse97/claude-skills/tree/main/engineering-team/senior-computer-vision
Command: npx skills add https://github.com/Patasse97/claude-skills --skill senior-computer-vision-patasse97

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Production-grade guidance for building, optimizing, and deploying computer vision systems, from dataset curation to model deployment.

Core Features & Use Cases

  • End-to-end CV workflows covering object detection, segmentation, and production deployment.
  • Templates, architecture guidance, and references for training, optimization, and serving.
  • Real-world use case: teams can follow structured steps to train a detector, optimize it with quantization/pruning, and deploy to a serving platform.

Quick Start

Run the quick-start workflow to generate training configurations, benchmark models, and assemble CV datasets using the included scripts.

Frequently Asked Questions about senior-computer-vision

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

FAQPage Schema
How do I build a production computer vision pipeline from scratch?▼

You can build a production computer vision pipeline by using structured workflows that automate dataset preparation, training, benchmarking, quantization, and serving for object detection and segmentation models.

Can I deploy and optimize object detection models using ONNX runtime?▼

Yes, the workflow supports optimizing object detection models through quantization and pruning, then exporting and serving them using ONNX and onnxruntime for production deployment.

Does this workflow support training models with Detectron2 and MMDetection?▼

Yes, the workflow supports training and benchmarking computer vision models across multiple frameworks, specifically including Ultralytics, Detectron2, and MMDetection for object detection and segmentation tasks.

What is the best way to prepare a CV dataset for production deployment?▼

The best way to prepare a CV dataset is to use the included scripts to assemble, curate, and structure your data, generating the necessary training configurations before benchmarking and deploying your model.

Do I need PyTorch and NumPy to run the model quantization scripts?▼

Yes, you need PyTorch and NumPy installed, along with ONNX and YAML, as these are the core dependencies required to execute the training, quantization, and deployment scripts.

How does quantization improve computer vision model serving?▼

Quantization improves computer vision model serving by reducing model size and inference latency, optimizing the trained detector or segmentation model for efficient deployment in production environments.

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
handsomelong922handsomelong922

serving-llms-vllm

Deploy scalable LLM serving with vLLM for OpenAI-compatible endpoints.

Community
Advanced
emilneuraz-aiemilneuraz-ai

embedding-strategies

Identify and compare embedding models to optimize semantic search performance for RAG pipelines and multilingual data.

Community
Advanced
michaelalbermichaelalber
2

edge-cv-pipeline

Build optimized computer vision pipelines for edge devices like Jetson and Raspberry Pi.

Community
Advanced