All Agent Skills

Otheralirezarezvani-skills

senior-computer-vision

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Open in Skill HubView pinned source

3k est. installs25k stars

Estimated installs are a discovery signal based on public repository popularity and source completeness, not recorded Dokki installation events.

Skill provenance

Repository

alirezarezvani/claude-skills

Pinned commit

f2bac0a8f29b

License

MIT

Execution

Instructions only

Complete source instructions

SKILL.md

Senior Computer Vision Engineer

Production computer vision engineering skill for object detection, image segmentation, and visual AI system deployment.

Table of Contents

Quick Start

bash
# Generate training configuration for YOLO or Faster R-CNNpython scripts/vision_model_trainer.py models/ --task detection --arch yolov8
# Analyze model for optimization opportunities (quantization, pruning)python scripts/inference_optimizer.py model.pt --target onnx --benchmark
# Build dataset pipeline with augmentationspython scripts/dataset_pipeline_builder.py images/ --format coco --augment

Core Expertise

This skill provides guidance on:

  • Object Detection: YOLO family (v5-v11), Faster R-CNN, DETR, RT-DETR
  • Instance Segmentation: Mask R-CNN, YOLACT, SOLOv2
  • Semantic Segmentation: DeepLabV3+, SegFormer, SAM (Segment Anything)
  • Image Classification: ResNet, EfficientNet, Vision Transformers (ViT, DeiT)
  • Video Analysis: Object tracking (ByteTrack, SORT), action recognition
  • 3D Vision: Depth estimation, point cloud processing, NeRF
  • Production Deployment: ONNX, TensorRT, OpenVINO, CoreML

Tech Stack

CategoryTechnologies
FrameworksPyTorch, torchvision, timm
DetectionUltralytics (YOLO), Detectron2, MMDetection
Segmentationsegment-anything, mmsegmentation
OptimizationONNX, TensorRT, OpenVINO, torch.compile
Image ProcessingOpenCV, Pillow, albumentations
AnnotationCVAT, Label Studio, Roboflow
Experiment TrackingMLflow, Weights & Biases
ServingTriton Inference Server, TorchServe

Workflow 1: Object Detection Pipeline

Use this workflow when building an object detection system from scratch.

Step 1: Define Detection Requirements

Analyze the detection task requirements:

Detection Requirements Analysis:- Target objects: [list specific classes to detect]- Real-time requirement: [yes/no, target FPS]- Accuracy priority: [speed vs accuracy trade-off]- Deployment target: [cloud GPU, edge device, mobile]- Dataset size: [number of images, annotations per class]

Step 2: Select Detection Architecture

Choose architecture based on requirements:

RequirementRecommended ArchitectureWhy
Real-time (>30 FPS)YOLOv8/v11, RT-DETRSingle-stage, optimized for speed
High accuracyFaster R-CNN, DINOTwo-stage, better localization
Small objectsYOLO + SAHI, Faster R-CNN + FPNMulti-scale detection
Edge deploymentYOLOv8n, MobileNetV3-SSDLightweight architectures
Transformer-basedDETR, DINO, RT-DETREnd-to-end, no NMS required

Step 3: Prepare Dataset

Convert annotations to required format:

bash
# COCO format (recommended)python scripts/dataset_pipeline_builder.py data/images/ \    --annotations data/labels/ \    --format coco \    --split 0.8 0.1 0.1 \    --output data/coco/
# Verify datasetpython -c "from pycocotools.coco import COCO; coco = COCO('data/coco/train.json'); print(f'Images: {len(coco.imgs)}, Categories: {len(coco.cats)}')"

Step 4: Configure Training

Generate training configuration:

bash
# For Ultralytics YOLOpython scripts/vision_model_trainer.py data/coco/ \    --task detection \    --arch yolov8m \    --epochs 100 \    --batch 16 \    --imgsz 640 \    --output configs/
# For Detectron2python scripts/vision_model_trainer.py data/coco/ \    --task detection \    --arch faster_rcnn_R_50_FPN \    --framework detectron2 \    --output configs/

Step 5: Train and Validate

bash
# Ultralytics trainingyolo detect train data=data.yaml model=yolov8m.pt epochs=100 imgsz=640
# Detectron2 trainingpython train_net.py --config-file configs/faster_rcnn.yaml --num-gpus 1
# Validate on test setyolo detect val model=runs/detect/train/weights/best.pt data=data.yaml

Step 6: Evaluate Results

Key metrics to analyze:

MetricTargetDescription
mAP@50>0.7Mean Average Precision at IoU 0.5
mAP@50:95>0.5COCO primary metric
Precision>0.8Low false positives
Recall>0.8Low missed detections
Inference time<33msFor 30 FPS real-time

Workflow 2: Model Optimization and Deployment

Use this workflow when preparing a trained model for production deployment.

Step 1: Benchmark Baseline Performance

bash
# Measure current model performancepython scripts/inference_optimizer.py model.pt \    --benchmark \    --input-size 640 640 \    --batch-sizes 1 4 8 16 \    --warmup 10 \    --iterations 100

Expected output:

Baseline Performance (PyTorch FP32):- Batch 1: 45.2ms (22.1 FPS)- Batch 4: 89.4ms (44.7 FPS)- Batch 8: 165.3ms (48.4 FPS)- Memory: 2.1 GB- Parameters: 25.9M

Step 2: Select Optimization Strategy

Deployment TargetOptimization Path
NVIDIA GPU (cloud)PyTorch → ONNX → TensorRT FP16
NVIDIA GPU (edge)PyTorch → TensorRT INT8
Intel CPUPyTorch → ONNX → OpenVINO
Apple SiliconPyTorch → CoreML
Generic CPUPyTorch → ONNX Runtime
MobilePyTorch → TFLite or ONNX Mobile

Step 3: Export to ONNX

bash
# Export with dynamic batch sizepython scripts/inference_optimizer.py model.pt \    --export onnx \    --input-size 640 640 \    --dynamic-batch \    --simplify \    --output model.onnx
# Verify ONNX modelpython -c "import onnx; model = onnx.load('model.onnx'); onnx.checker.check_model(model); print('ONNX model valid')"

Step 4: Apply Quantization (Optional)

For INT8 quantization with calibration:

bash
# Generate calibration datasetpython scripts/inference_optimizer.py model.onnx \    --quantize int8 \    --calibration-data data/calibration/ \    --calibration-samples 500 \    --output model_int8.onnx

Quantization impact analysis:

PrecisionSizeSpeedAccuracy Drop
FP32100%1x0%
FP1650%1.5-2x<0.5%
INT825%2-4x1-3%

Step 5: Convert to Target Runtime

bash
# TensorRT (NVIDIA GPU)trtexec --onnx=model.onnx --saveEngine=model.engine --fp16
# OpenVINO (Intel)mo --input_model model.onnx --output_dir openvino/
# CoreML (Apple)python -c "import coremltools as ct; model = ct.convert('model.onnx'); model.save('model.mlpackage')"

Step 6: Benchmark Optimized Model

bash
python scripts/inference_optimizer.py model.engine \    --benchmark \    --runtime tensorrt \    --compare model.pt

Expected speedup:

Optimization Results:- Original (PyTorch FP32): 45.2ms- Optimized (TensorRT FP16): 12.8ms- Speedup: 3.5x- Accuracy change: -0.3% mAP

Workflow 3: Custom Dataset Preparation

Use this workflow when preparing a computer vision dataset for training.

Step 1: Audit Raw Data

bash
# Analyze image datasetpython scripts/dataset_pipeline_builder.py data/raw/ \    --analyze \    --output analysis/

Analysis report includes:

Dataset Analysis:- Total images: 5,234- Image sizes: 640x480 to 4096x3072 (variable)- Formats: JPEG (4,891), PNG (343)- Corrupted: 12 files- Duplicates: 45 pairs
Annotation Analysis:- Format detected: Pascal VOC XML- Total annotations: 28,456- Classes: 5 (car, person, bicycle, dog, cat)- Distribution: car (12,340), person (8,234), bicycle (3,456), dog (2,890), cat (1,536)- Empty images: 234

Step 2: Clean and Validate

bash
# Remove corrupted and duplicate imagespython scripts/dataset_pipeline_builder.py data/raw/ \    --clean \    --remove-corrupted \    --remove-duplicates \    --output data/cleaned/

Step 3: Convert Annotation Format

bash
# Convert VOC to COCO formatpython scripts/dataset_pipeline_builder.py data/cleaned/ \    --annotations data/annotations/ \    --input-format voc \    --output-format coco \    --output data/coco/

Supported format conversions:

FromTo
Pascal VOC XMLCOCO JSON
YOLO TXTCOCO JSON
COCO JSONYOLO TXT
LabelMe JSONCOCO JSON
CVAT XMLCOCO JSON

Step 4: Apply Augmentations

bash
# Generate augmentation configpython scripts/dataset_pipeline_builder.py data/coco/ \    --augment \    --aug-config configs/augmentation.yaml \    --output data/augmented/

Recommended augmentations for detection:

yaml
# configs/augmentation.yamlaugmentations:  geometric:    - horizontal_flip: { p: 0.5 }    - vertical_flip: { p: 0.1 }  # Only if orientation invariant    - rotate: { limit: 15, p: 0.3 }    - scale: { scale_limit: 0.2, p: 0.5 }
  color:    - brightness_contrast: { brightness_limit: 0.2, contrast_limit: 0.2, p: 0.5 }    - hue_saturation: { hue_shift_limit: 20, sat_shift_limit: 30, p: 0.3 }    - blur: { blur_limit: 3, p: 0.1 }
  advanced:    - mosaic: { p: 0.5 }  # YOLO-style mosaic    - mixup: { p: 0.1 }   # Image mixing    - cutout: { num_holes: 8, max_h_size: 32, max_w_size: 32, p: 0.3 }

Step 5: Create Train/Val/Test Splits

bash
python scripts/dataset_pipeline_builder.py data/augmented/ \    --split 0.8 0.1 0.1 \    --stratify \    --seed 42 \    --output data/final/

Split strategy guidelines:

Dataset SizeTrainValTest
<1,000 images70%15%15%
1,000-10,00080%10%10%
>10,00090%5%5%

Step 6: Generate Dataset Configuration

bash
# For Ultralytics YOLOpython scripts/dataset_pipeline_builder.py data/final/ \    --generate-config yolo \    --output data.yaml
# For Detectron2python scripts/dataset_pipeline_builder.py data/final/ \    --generate-config detectron2 \    --output detectron2_config.py

Architecture Selection Guide

Object Detection Architectures

ArchitectureSpeedAccuracyBest For
YOLOv8n1.2ms37.3 mAPEdge, mobile, real-time
YOLOv8s2.1ms44.9 mAPBalanced speed/accuracy
YOLOv8m4.2ms50.2 mAPGeneral purpose
YOLOv8l6.8ms52.9 mAPHigh accuracy
YOLOv8x10.1ms53.9 mAPMaximum accuracy
RT-DETR-L5.3ms53.0 mAPTransformer, no NMS
Faster R-CNN R5046ms40.2 mAPTwo-stage, high quality
DINO-4scale85ms49.0 mAPSOTA transformer

Segmentation Architectures

ArchitectureTypeSpeedBest For
YOLOv8-segInstance4.5msReal-time instance seg
Mask R-CNNInstance67msHigh-quality masks
SAMPromptable50msZero-shot segmentation
DeepLabV3+Semantic25msScene parsing
SegFormerSemantic15msEfficient semantic seg

CNN vs Vision Transformer Trade-offs

AspectCNN (YOLO, R-CNN)ViT (DETR, DINO)
Training data needed1K-10K images10K-100K+ images
Training timeFastSlow (needs more epochs)
Inference speedFasterSlower
Small objectsGood with FPNNeeds multi-scale
Global contextLimitedExcellent
Positional encodingImplicitExplicit

Reference Documentation

→ See references/reference-docs-and-commands.md for details

Performance Targets

MetricReal-timeHigh AccuracyEdge
FPS>30>10>15
mAP@50>0.6>0.8>0.5
Latency P99<50ms<150ms<100ms
GPU Memory<4GB<8GB<2GB
Model Size<50MB<200MB<20MB

Resources

  • Architecture Guide: references/computer_vision_architectures.md
  • Optimization Guide: references/object_detection_optimization.md
  • Deployment Guide: references/production_vision_systems.md
  • Scripts: scripts/ directory for automation tools

Same repository

Related Skills

Start your company of agents
today.

Free to start. Your first team is one sentence away.

Start free