Can this skill help with deploying models to production?

Yes, it provides dedicated workflows for model optimization using ONNX, TensorRT, OpenVINO, and CoreML to ensure high-performance inference on various hardware targets.

How does it assist in choosing the right architecture?

The skill features an Architecture Selection Guide that compares speed, accuracy, and use cases for various CNN and Vision Transformer models to help you make informed decisions.

Which frameworks does this computer vision skill support?

It supports leading industry frameworks including PyTorch, torchvision, Ultralytics (YOLO), Detectron2, MMDetection, and Segment Anything (SAM).

Does it handle dataset preparation and annotation formats?

Absolutely. It includes tools for converting between formats like COCO, Pascal VOC, and YOLO TXT, as well as cleaning raw data and applying advanced augmentations.

Senior Computer Vision Engineer

Name: Senior Computer Vision Engineer
Author: oabdelmaksoud

byoabdelmaksoud

0•

Ciencia de Datos y ML

Architects and deploys production-grade computer vision systems for object detection, image segmentation, and visual AI tasks.

The Senior Computer Vision Engineer skill provides a comprehensive framework for building, training, and deploying advanced visual AI systems. It offers expert-level guidance on selecting architectures like YOLO, Faster R-CNN, and Vision Transformers, while providing automated workflows for dataset curation, annotation conversion, and advanced augmentations. Beyond training, the skill excels at productionizing models through rigorous optimization paths involving ONNX, TensorRT, and OpenVINO, ensuring your vision pipelines meet real-world performance requirements on both cloud and edge hardware.

Características Principales

01Real-time inference benchmarking and deployment strategy mapping

02Expert architecture selection guidance for CNNs and Vision Transformers

03Production-grade model optimization using ONNX, TensorRT, and OpenVINO

04Automated dataset curation, annotation conversion, and augmentation workflows

05End-to-end object detection and instance segmentation pipeline automation

060 GitHub stars

Casos de Uso

01Building real-time object detection systems for edge devices using YOLO or RT-DETR

02Preparing and cleaning custom datasets with complex augmentation strategies and format conversions

03Converting research models to high-performance inference engines for production deployment

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oabdelmaksoud/superclaw senior-computer-vision

For use in Claude.ai and ChatGPT

Características Principales

01Real-time inference benchmarking and deployment strategy mapping

02Expert architecture selection guidance for CNNs and Vision Transformers

03Production-grade model optimization using ONNX, TensorRT, and OpenVINO

04Automated dataset curation, annotation conversion, and augmentation workflows

05End-to-end object detection and instance segmentation pipeline automation

060 GitHub stars

Casos de Uso

01Building real-time object detection systems for edge devices using YOLO or RT-DETR

02Preparing and cleaning custom datasets with complex augmentation strategies and format conversions

03Converting research models to high-performance inference engines for production deployment