senior-computer-visionComputer 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.
Install via ClawdBot CLI:
clawdbot install alirezarezvani/senior-computer-visionProduction computer vision engineering skill for object detection, image segmentation, and visual AI system deployment.
# Generate training configuration for YOLO or Faster R-CNN
python 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 augmentations
python scripts/dataset_pipeline_builder.py images/ --format coco --augmentThis skill provides guidance on:
| Category | Technologies |
|----------|--------------|
| Frameworks | PyTorch, torchvision, timm |
| Detection | Ultralytics (YOLO), Detectron2, MMDetection |
| Segmentation | segment-anything, mmsegmentation |
| Optimization | ONNX, TensorRT, OpenVINO, torch.compile |
| Image Processing | OpenCV, Pillow, albumentations |
| Annotation | CVAT, Label Studio, Roboflow |
| Experiment Tracking | MLflow, Weights & Biases |
| Serving | Triton Inference Server, TorchServe |
Use this workflow when building an object detection system from scratch.
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]Choose architecture based on requirements:
| Requirement | Recommended Architecture | Why |
|-------------|-------------------------|-----|
| Real-time (>30 FPS) | YOLOv8/v11, RT-DETR | Single-stage, optimized for speed |
| High accuracy | Faster R-CNN, DINO | Two-stage, better localization |
| Small objects | YOLO + SAHI, Faster R-CNN + FPN | Multi-scale detection |
| Edge deployment | YOLOv8n, MobileNetV3-SSD | Lightweight architectures |
| Transformer-based | DETR, DINO, RT-DETR | End-to-end, no NMS required |
Convert annotations to required format:
# 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 dataset
python -c "from pycocotools.coco import COCO; coco = COCO('data/coco/train.json'); print(f'Images: {len(coco.imgs)}, Categories: {len(coco.cats)}')"Generate training configuration:
# For Ultralytics YOLO
python scripts/vision_model_trainer.py data/coco/ \
--task detection \
--arch yolov8m \
--epochs 100 \
--batch 16 \
--imgsz 640 \
--output configs/
# For Detectron2
python scripts/vision_model_trainer.py data/coco/ \
--task detection \
--arch faster_rcnn_R_50_FPN \
--framework detectron2 \
--output configs/# Ultralytics training
yolo detect train data=data.yaml model=yolov8m.pt epochs=100 imgsz=640
# Detectron2 training
python train_net.py --config-file configs/faster_rcnn.yaml --num-gpus 1
# Validate on test set
yolo detect val model=runs/detect/train/weights/best.pt data=data.yamlKey metrics to analyze:
| Metric | Target | Description |
|--------|--------|-------------|
| mAP@50 | >0.7 | Mean Average Precision at IoU 0.5 |
| mAP@50:95 | >0.5 | COCO primary metric |
| Precision | >0.8 | Low false positives |
| Recall | >0.8 | Low missed detections |
| Inference time | <33ms | For 30 FPS real-time |
Use this workflow when preparing a trained model for production deployment.
# Measure current model performance
python scripts/inference_optimizer.py model.pt \
--benchmark \
--input-size 640 640 \
--batch-sizes 1 4 8 16 \
--warmup 10 \
--iterations 100Expected 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| Deployment Target | Optimization Path |
|-------------------|-------------------|
| NVIDIA GPU (cloud) | PyTorch → ONNX → TensorRT FP16 |
| NVIDIA GPU (edge) | PyTorch → TensorRT INT8 |
| Intel CPU | PyTorch → ONNX → OpenVINO |
| Apple Silicon | PyTorch → CoreML |
| Generic CPU | PyTorch → ONNX Runtime |
| Mobile | PyTorch → TFLite or ONNX Mobile |
# Export with dynamic batch size
python scripts/inference_optimizer.py model.pt \
--export onnx \
--input-size 640 640 \
--dynamic-batch \
--simplify \
--output model.onnx
# Verify ONNX model
python -c "import onnx; model = onnx.load('model.onnx'); onnx.checker.check_model(model); print('ONNX model valid')"For INT8 quantization with calibration:
# Generate calibration dataset
python scripts/inference_optimizer.py model.onnx \
--quantize int8 \
--calibration-data data/calibration/ \
--calibration-samples 500 \
--output model_int8.onnxQuantization impact analysis:
| Precision | Size | Speed | Accuracy Drop |
|-----------|------|-------|---------------|
| FP32 | 100% | 1x | 0% |
| FP16 | 50% | 1.5-2x | <0.5% |
| INT8 | 25% | 2-4x | 1-3% |
# 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')"python scripts/inference_optimizer.py model.engine \
--benchmark \
--runtime tensorrt \
--compare model.ptExpected speedup:
Optimization Results:
- Original (PyTorch FP32): 45.2ms
- Optimized (TensorRT FP16): 12.8ms
- Speedup: 3.5x
- Accuracy change: -0.3% mAPUse this workflow when preparing a computer vision dataset for training.
# Analyze image dataset
python 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# Remove corrupted and duplicate images
python scripts/dataset_pipeline_builder.py data/raw/ \
--clean \
--remove-corrupted \
--remove-duplicates \
--output data/cleaned/# Convert VOC to COCO format
python scripts/dataset_pipeline_builder.py data/cleaned/ \
--annotations data/annotations/ \
--input-format voc \
--output-format coco \
--output data/coco/Supported format conversions:
| From | To |
|------|-----|
| Pascal VOC XML | COCO JSON |
| YOLO TXT | COCO JSON |
| COCO JSON | YOLO TXT |
| LabelMe JSON | COCO JSON |
| CVAT XML | COCO JSON |
# Generate augmentation config
python scripts/dataset_pipeline_builder.py data/coco/ \
--augment \
--aug-config configs/augmentation.yaml \
--output data/augmented/Recommended augmentations for detection:
# configs/augmentation.yaml
augmentations:
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 }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 Size | Train | Val | Test |
|--------------|-------|-----|------|
| <1,000 images | 70% | 15% | 15% |
| 1,000-10,000 | 80% | 10% | 10% |
| >10,000 | 90% | 5% | 5% |
# For Ultralytics YOLO
python scripts/dataset_pipeline_builder.py data/final/ \
--generate-config yolo \
--output data.yaml
# For Detectron2
python scripts/dataset_pipeline_builder.py data/final/ \
--generate-config detectron2 \
--output detectron2_config.py| Architecture | Speed | Accuracy | Best For |
|--------------|-------|----------|----------|
| YOLOv8n | 1.2ms | 37.3 mAP | Edge, mobile, real-time |
| YOLOv8s | 2.1ms | 44.9 mAP | Balanced speed/accuracy |
| YOLOv8m | 4.2ms | 50.2 mAP | General purpose |
| YOLOv8l | 6.8ms | 52.9 mAP | High accuracy |
| YOLOv8x | 10.1ms | 53.9 mAP | Maximum accuracy |
| RT-DETR-L | 5.3ms | 53.0 mAP | Transformer, no NMS |
| Faster R-CNN R50 | 46ms | 40.2 mAP | Two-stage, high quality |
| DINO-4scale | 85ms | 49.0 mAP | SOTA transformer |
| Architecture | Type | Speed | Best For |
|--------------|------|-------|----------|
| YOLOv8-seg | Instance | 4.5ms | Real-time instance seg |
| Mask R-CNN | Instance | 67ms | High-quality masks |
| SAM | Promptable | 50ms | Zero-shot segmentation |
| DeepLabV3+ | Semantic | 25ms | Scene parsing |
| SegFormer | Semantic | 15ms | Efficient semantic seg |
| Aspect | CNN (YOLO, R-CNN) | ViT (DETR, DINO) |
|--------|-------------------|------------------|
| Training data needed | 1K-10K images | 10K-100K+ images |
| Training time | Fast | Slow (needs more epochs) |
| Inference speed | Faster | Slower |
| Small objects | Good with FPN | Needs multi-scale |
| Global context | Limited | Excellent |
| Positional encoding | Implicit | Explicit |
See references/computer_vision_architectures.md for:
See references/object_detection_optimization.md for:
See references/production_vision_systems.md for:
# Training
yolo detect train data=coco.yaml model=yolov8m.pt epochs=100 imgsz=640
# Validation
yolo detect val model=best.pt data=coco.yaml
# Inference
yolo detect predict model=best.pt source=images/ save=True
# Export
yolo export model=best.pt format=onnx simplify=True dynamic=True# Training
python train_net.py --config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml \
--num-gpus 1 OUTPUT_DIR ./output
# Evaluation
python train_net.py --config-file configs/faster_rcnn.yaml --eval-only \
MODEL.WEIGHTS output/model_final.pth
# Inference
python demo.py --config-file configs/faster_rcnn.yaml \
--input images/*.jpg --output results/ \
--opts MODEL.WEIGHTS output/model_final.pth# Training
python tools/train.py configs/faster_rcnn/faster-rcnn_r50_fpn_1x_coco.py
# Testing
python tools/test.py configs/faster_rcnn.py checkpoints/latest.pth --eval bbox
# Inference
python demo/image_demo.py demo.jpg configs/faster_rcnn.py checkpoints/latest.pth# ONNX export and simplify
python -c "import torch; model = torch.load('model.pt'); torch.onnx.export(model, torch.randn(1,3,640,640), 'model.onnx', opset_version=17)"
python -m onnxsim model.onnx model_sim.onnx
# TensorRT conversion
trtexec --onnx=model.onnx --saveEngine=model.engine --fp16 --workspace=4096
# Benchmark
trtexec --loadEngine=model.engine --batch=1 --iterations=1000 --avgRuns=100| Metric | Real-time | High Accuracy | Edge |
|--------|-----------|---------------|------|
| 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 |
references/computer_vision_architectures.mdreferences/object_detection_optimization.mdreferences/production_vision_systems.mdscripts/ directory for automation toolsGenerated Mar 1, 2026
Automates stock counting and shelf monitoring using real-time object detection on edge devices. Detects product placement, out-of-stock items, and misplaced goods to optimize inventory and reduce manual audits.
Implements visual inspection systems to detect defects in production lines with high-precision segmentation models. Identifies anomalies like cracks or misalignments, ensuring product quality and reducing waste.
Builds detection pipelines for real-time object and pedestrian tracking in self-driving cars. Uses YOLO or DETR architectures optimized with TensorRT for low-latency inference in safety-critical environments.
Develops AI systems for analyzing medical scans, such as tumor detection in MRI images using Mask R-CNN. Supports diagnosis with high-accuracy segmentation and integrates with hospital workflows.
Deploys video analysis pipelines for object tracking and activity recognition in security cameras. Uses ByteTrack for real-time monitoring and alerts on suspicious events in public or private spaces.
Offers cloud-based APIs for object detection and segmentation, charging per inference or subscription. Targets businesses needing scalable vision solutions without in-house expertise, with revenue from usage fees.
Provides tailored computer vision solutions by training models on client datasets for specific use cases. Generates revenue through project-based contracts and ongoing maintenance support.
Licenses optimized vision models (e.g., via ONNX or TensorRT) for deployment on edge hardware like cameras or IoT devices. Revenue comes from one-time licenses or royalties per device sold.
💬 Integration Tip
Use ONNX or TensorRT for production deployment to optimize inference speed and memory usage, ensuring compatibility with cloud or edge environments.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.