{"id":"08bb4af3-c48e-47c5-a11a-7d2cb6447fb6","entityType":"agent","slug":"clawhub-skills-alirezarezvani-senior-computer-vision","name":"senior-computer-vision","canonicalUrl":"https://www.xpersona.co/agent/clawhub-skills-alirezarezvani-senior-computer-vision","canonicalPath":"/agent/clawhub-skills-alirezarezvani-senior-computer-vision","generatedAt":"2026-10-09T19:22:36.897Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"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. --- name: senior-computer-vision description: 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 pipel","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"clawhub skill install skills:alirezarezvani:senior-computer-vision","sourceUrl":"https://github.com/openclaw/skills/tree/main/skills/alirezarezvani/senior-computer-vision","homepage":null,"primaryLinks":[{"label":"View on ClawHub","url":"https://github.com/openclaw/skills/tree/main/skills/alirezarezvani/senior-computer-vision","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":50,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No source adoption metrics were available."},"stars":null,"forks":null,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-02-25T05:59:45.412Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-25T05:59:45.412Z","lastIndexedAt":null,"nextCrawlAt":"2026-02-26T05:59:45.412Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install skills:alirezarezvani:senior-computer-vision","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T19:22:36.897Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-skills-alirezarezvani-senior-computer-vision/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"---\nname: senior-computer-vision\ndescription: 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.\n---\n\n# Senior Computer Vision Engineer\n\nProduction computer vision engineering skill for object detection, image segmentation, and visual AI system deployment.\n\n## Table of Contents\n\n- [Quick Start](#quick-start)\n- [Core Expertise](#core-expertise)\n- [Tech Stack](#tech-stack)\n- [Workflow 1: Object Detection Pipeline](#workflow-1-object-detection-pipeline)\n- [Workflow 2: Model Optimization and Deployment](#workflow-2-model-optimization-and-deployment)\n- [Workflow 3: Custom Dataset Preparation](#workflow-3-custom-dataset-preparation)\n- [Architecture Selection Guide](#architecture-selection-guide)\n- [Reference Documentation](#reference-documentation)\n- [Common Commands](#common-commands)\n\n## Quick Start\n\n```bash\n# Generate training configuration for YOLO or Faster R-CNN\npython scripts/vision_model_trainer.py models/ --task detection --arch yolov8\n\n# Analyze model for optimization opportunities (quantization, pruning)\npython scripts/inference_optimizer.py model.pt --target onnx --benchmark\n\n# Build dataset pipeline with augmentations\npython scripts/dataset_pipeline_builder.py images/ --format coco --augment\n```\n\n## Core Expertise\n\nThis skill provides guidance on:\n\n- **Object Detection**: YOLO family (v5-v11), Faster R-CNN, DETR, RT-DETR\n- **Instance Segmentation**: Mask R-CNN, YOLACT, SOLOv2\n- **Semantic Segmentation**: DeepLabV3+, SegFormer, SAM (Segment Anything)\n- **Image Classification**: ResNet, EfficientNet, Vision Transformers (ViT, DeiT)\n- **Video Analysis**: Object tracking (ByteTrack, SORT), action recognition\n- **3D Vision**: Depth estimation, point cloud processing, NeRF\n- **Production Deployment**: ONNX, TensorRT, OpenVINO, CoreML\n\n## Tech Stack\n\n| Category | Technologies |\n|----------|--------------|\n| Frameworks | PyTorch, torchvision, timm |\n| Detection | Ultralytics (YOLO), Detectron2, MMDetection |\n| Segmentation | segment-anything, mmsegmentation |\n| Optimization | ONNX, TensorRT, OpenVINO, torch.compile |\n| Image Processing | OpenCV, Pillow, albumentations |\n| Annotation | CVAT, Label Studio, Roboflow |\n| Experiment Tracking | MLflow, Weights & Biases |\n| Serving | Triton Inference Server, TorchServe |\n\n## Workflow 1: Object Detection Pipeline\n\nUse this workflow when building an object detection system from scratch.\n\n### Step 1: Define Detection Requirements\n\nAnalyze the detection task requirements:\n\n```\nDetection Requirements Analysis:\n- Target objects: [list specific classes to detect]\n- Real-time requirement: [yes/no, target FPS]\n- Accuracy priority: [speed vs accuracy trade-off]\n- Deployment target: [cloud GPU, edge device, mobile]\n- Dataset size: [number of images, annotations per class]\n```\n\n### Step 2: Select Detection Architecture\n\nChoose architecture based on requirements:\n\n| Requirement | Recommended Architecture | Why |\n|-------------|-------------------------|-----|\n| Real-time (>30 FPS) | YOLOv8/v11, RT-DETR | Single-stage, optimized for speed |\n| High accuracy | Faster R-CNN, DINO | Two-stage, better localization |\n| Small objects | YOLO + SAHI, Faster R-CNN + FPN | Multi-scale detection |\n| Edge deployment | YOLOv8n, MobileNetV3-SSD | Lightweight architectures |\n| Transformer-based | DETR, DINO, RT-DETR | End-to-end, no NMS required |\n\n### Step 3: Prepare Dataset\n\nConvert annotations to required format:\n\n```bash\n# COCO format (recommended)\npython scripts/dataset_pipeline_builder.py data/images/ \\\n    --annotations data/labels/ \\\n    --format coco \\\n    --split 0.8 0.1 0.1 \\\n    --output data/coco/\n\n# Verify dataset\npython -c \"from pycocotools.coco import COCO; coco = COCO('data/coco/train.json'); print(f'Images: {len(coco.imgs)}, Categories: {len(coco.cats)}')\"\n```\n\n### Step 4: Configure Training\n\nGenerate training configuration:\n\n```bash\n# For Ultralytics YOLO\npython scripts/vision_model_trainer.py data/coco/ \\\n    --task detection \\\n    --arch yolov8m \\\n    --epochs 100 \\\n    --batch 16 \\\n    --imgsz 640 \\\n    --output configs/\n\n# For Detectron2\npython scripts/vision_model_trainer.py data/coco/ \\\n    --task detection \\\n    --arch faster_rcnn_R_50_FPN \\\n    --framework detectron2 \\\n    --output configs/\n```\n\n### Step 5: Train and Validate\n\n```bash\n# Ultralytics training\nyolo detect train data=data.yaml model=yolov8m.pt epochs=100 imgsz=640\n\n# Detectron2 training\npython train_net.py --config-file configs/faster_rcnn.yaml --num-gpus 1\n\n# Validate on test set\nyolo detect val model=runs/detect/train/weights/best.pt data=data.yaml\n```\n\n### Step 6: Evaluate Results\n\nKey metrics to analyze:\n\n| Metric | Target | Description |\n|--------|--------|-------------|\n| mAP@50 | >0.7 | Mean Average Precision at IoU 0.5 |\n| mAP@50:95 | >0.5 | COCO primary metric |\n| Precision | >0.8 | Low false positives |\n| Recall | >0.8 | Low missed detections |\n| Inference time | <33ms | For 30 FPS real-time |\n\n## Workflow 2: Model Optimization and Deployment\n\nUse this workflow when preparing a trained model for production deployment.\n\n### Step 1: Benchmark Baseline Performance\n\n```bash\n# Measure current model performance\npython scripts/inference_optimizer.py model.pt \\\n    --benchmark \\\n    --input-size 640 640 \\\n    --batch-sizes 1 4 8 16 \\\n    --warmup 10 \\\n    --iterations 100\n```\n\nExpected output:\n\n```\nBaseline Performance (PyTorch FP32):\n- Batch 1: 45.2ms (22.1 FPS)\n- Batch 4: 89.4ms (44.7 FPS)\n- Batch 8: 165.3ms (48.4 FPS)\n- Memory: 2.1 GB\n- Parameters: 25.9M\n```\n\n### Step 2: Select Optimization Strategy\n\n| Deployment Target | Optimization Path |\n|-------------------|-------------------|\n| NVIDIA GPU (cloud) | PyTorch → ONNX → TensorRT FP16 |\n| NVIDIA GPU (edge) | PyTorch → TensorRT INT8 |\n| Intel CPU | PyTorch → ONNX → OpenVINO |\n| Apple Silicon | PyTorch → CoreML |\n| Generic CPU | PyTorch → ONNX Runtime |\n| Mobile | PyTorch → TFLite or ONNX Mobile |\n\n### Step 3: Export to ONNX\n\n```bash\n# Export with dynamic batch size\npython scripts/inference_optimizer.py model.pt \\\n    --export onnx \\\n    --input-size 640 640 \\\n    --dynamic-batch \\\n    --simplify \\\n    --output model.onnx\n\n# Verify ONNX model\npython -c \"import onnx; model = onnx.load('model.onnx'); onnx.checker.check_model(model); print('ONNX model valid')\"\n```\n\n### Step 4: Apply Quantization (Optional)\n\nFor INT8 quantization with calibration:\n\n```bash\n# Generate calibration dataset\npython scripts/inference_optimizer.py model.onnx \\\n    --quantize int8 \\\n    --calibration-data data/calibration/ \\\n    --calibration-samples 500 \\\n    --output model_int8.onnx\n```\n\nQuantization impact analysis:\n\n| Precision | Size | Speed | Accuracy Drop |\n|-----------|------|-------|---------------|\n| FP32 | 100% | 1x | 0% |\n| FP16 | 50% | 1.5-2x | <0.5% |\n| INT8 | 25% | 2-4x | 1-3% |\n\n### Step 5: Convert to Target Runtime\n\n```bash\n# TensorRT (NVIDIA GPU)\ntrtexec --onnx=model.onnx --saveEngine=model.engine --fp16\n\n# OpenVINO (Intel)\nmo --input_model model.onnx --output_dir openvino/\n\n# CoreML (Apple)\npython -c \"import coremltools as ct; model = ct.convert('model.onnx'); model.save('model.mlpackage')\"\n```\n\n### Step 6: Benchmark Optimized Model\n\n```bash\npython scripts/inference_optimizer.py model.engine \\\n    --benchmark \\\n    --runtime tensorrt \\\n    --compare model.pt\n```\n\nExpected speedup:\n\n```\nOptimization Results:\n- Original (PyTorch FP32): 45.2ms\n- Optimized (TensorRT FP16): 12.8ms\n- Speedup: 3.5x\n- Accuracy change: -0.3% mAP\n```\n\n## Workflow 3: Custom Dataset Preparation\n\nUse this workflow when preparing a computer vision dataset for training.\n\n### Step 1: Audit Raw Data\n\n```bash\n# Analyze image dataset\npython scripts/dataset_pipeline_builder.py data/raw/ \\\n    --analyze \\\n    --output analysis/\n```\n\nAnalysis report includes:\n\n```\nDataset Analysis:\n- Total images: 5,234\n- Image sizes: 640x480 to 4096x3072 (variable)\n- Formats: JPEG (4,891), PNG (343)\n- Corrupted: 12 files\n- Duplicates: 45 pairs\n\nAnnotation Analysis:\n- Format detected: Pascal VOC XML\n- Total annotations: 28,456\n- Classes: 5 (car, person, bicycle, dog, cat)\n- Distribution: car (12,340), person (8,234), bicycle (3,456), dog (2,890), cat (1,536)\n- Empty images: 234\n```\n\n### Step 2: Clean and Validate\n\n```bash\n# Remove corrupted and duplicate images\npython scripts/dataset_pipeline_builder.py data/raw/ \\\n    --clean \\\n    --remove-corrupted \\\n    --remove-duplicates \\\n    --output data/cleaned/\n```\n\n### Step 3: Convert Annotation Format\n\n```bash\n# Convert VOC to COCO format\npython scripts/dataset_pipeline_builder.py data/cleaned/ \\\n    --annotations data/annotations/ \\\n    --input-format voc \\\n    --output-format coco \\\n    --output data/coco/\n```\n\nSupported format conversions:\n\n| From | To |\n|------|-----|\n| Pascal VOC XML | COCO JSON |\n| YOLO TXT | COCO JSON |\n| COCO JSON | YOLO TXT |\n| LabelMe JSON | COCO JSON |\n| CVAT XML | COCO JSON |\n\n### Step 4: Apply Augmentations\n\n```bash\n# Generate augmentation config\npython scripts/dataset_pipeline_builder.py data/coco/ \\\n    --augment \\\n    --aug-config configs/augmentation.yaml \\\n    --output data/augmented/\n```\n\nRecommended augmentations for detection:\n\n```yaml\n# configs/augmentation.yaml\naugmentations:\n  geometric:\n    - horizontal_flip: { p: 0.5 }\n    - vertical_flip: { p: 0.1 }  # Only if orientation invariant\n    - rotate: { limit: 15, p: 0.3 }\n    - scale: { scale_limit: 0.2, p: 0.5 }\n\n  color:\n    - brightness_contrast: { brightness_limit: 0.2, contrast_limit: 0.2, p: 0.5 }\n    - hue_saturation: { hue_shift_limit: 20, sat_shift_limit: 30, p: 0.3 }\n    - blur: { blur_limit: 3, p: 0.1 }\n\n  advanced:\n    - mosaic: { p: 0.5 }  # YOLO-style mosaic\n    - mixup: { p: 0.1 }   # Image mixing\n    - cutout: { num_holes: 8, max_h_size: 32, max_w_size: 32, p: 0.3 }\n```\n\n### Step 5: Create Train/Val/Test Splits\n\n```bash\npython scripts/dataset_pipeline_builder.py data/augmented/ \\\n    --split 0.8 0.1 0.1 \\\n    --stratify \\\n    --seed 42 \\\n    --output data/final/\n```\n\nSplit strategy guidelines:\n\n| Dataset Size | Train | Val | Test |\n|--------------|-------|-----|------|\n| <1,000 images | 70% | 15% | 15% |\n| 1,000-10,000 | 80% | 10% | 10% |\n| >10,000 | 90% | 5% | 5% |\n\n### Step 6: Generate Dataset Configuration\n\n```bash\n# For Ultralytics YOLO\npython scripts/dataset_pipeline_builder.py data/final/ \\\n    --generate-config yolo \\\n    --output data.yaml\n\n# For Detectron2\npython scripts/dataset_pipeline_builder.py data/final/ \\\n    --generate-config detectron2 \\\n    --output detectron2_config.py\n```\n\n## Architecture Selection Guide\n\n### Object Detection Architectures\n\n| Architecture | Speed | Accuracy | Best For |\n|--------------|-------|----------|----------|\n| YOLOv8n | 1.2ms | 37.3 mAP | Edge, mobile, real-time |\n| YOLOv8s | 2.1ms | 44.9 mAP | Balanced speed/accuracy |\n| YOLOv8m | 4.2ms | 50.2 mAP | General purpose |\n| YOLOv8l | 6.8ms | 52.9 mAP | High accuracy |\n| YOLOv8x | 10.1ms | 53.9 mAP | Maximum accuracy |\n| RT-DETR-L | 5.3ms | 53.0 mAP | Transformer, no NMS |\n| Faster R-CNN R50 | 46ms | 40.2 mAP | Two-stage, high quality |\n| DINO-4scale | 85ms | 49.0 mAP | SOTA transformer |\n\n### Segmentation Architectures\n\n| Architecture | Type | Speed | Best For |\n|--------------|------|-------|----------|\n| YOLOv8-seg | Instance | 4.5ms | Real-time instance seg |\n| Mask R-CNN | Instance | 67ms | High-quality masks |\n| SAM | Promptable | 50ms | Zero-shot segmentation |\n| DeepLabV3+ | Semantic | 25ms | Scene parsing |\n| SegFormer | Semantic | 15ms | Efficient semantic seg |\n\n### CNN vs Vision Transformer Trade-offs\n\n| Aspect | CNN (YOLO, R-CNN) | ViT (DETR, DINO) |\n|--------|-------------------|------------------|\n| Training data needed | 1K-10K images | 10K-100K+ images |\n| Training time | Fast | Slow (needs more epochs) |\n| Inference speed | Faster | Slower |\n| Small objects | Good with FPN | Needs multi-scale |\n| Global context | Limited | Excellent |\n| Positional encoding | Implicit | Explicit |\n\n## Reference Documentation\n\n### 1. Computer Vision Architectures\n\nSee `references/computer_vision_architectures.md` for:\n\n- CNN backbone architectures (ResNet, EfficientNet, ConvNeXt)\n- Vision Transformer variants (ViT, DeiT, Swin)\n- Detection heads (anchor-based vs anchor-free)\n- Feature Pyramid Networks (FPN, BiFPN, PANet)\n- Neck architectures for multi-scale detection\n\n### 2. Object Detection Optimization\n\nSee `references/object_detection_optimization.md` for:\n\n- Non-Maximum Suppression variants (NMS, Soft-NMS, DIoU-NMS)\n- Anchor optimization and anchor-free alternatives\n- Loss function design (focal loss, GIoU, CIoU, DIoU)\n- Training strategies (warmup, cosine annealing, EMA)\n- Data augmentation for detection (mosaic, mixup, copy-paste)\n\n### 3. Production Vision Systems\n\nSee `references/production_vision_systems.md` for:\n\n- ONNX export and optimization\n- TensorRT deployment pipeline\n- Batch inference optimization\n- Edge device deployment (Jetson, Intel NCS)\n- Model serving with Triton\n- Video processing pipelines\n\n## Common Commands\n\n### Ultralytics YOLO\n\n```bash\n# Training\nyolo detect train data=coco.yaml model=yolov8m.pt epochs=100 imgsz=640\n\n# Validation\nyolo detect val model=best.pt data=coco.yaml\n\n# Inference\nyolo detect predict model=best.pt source=images/ save=True\n\n# Export\nyolo export model=best.pt format=onnx simplify=True dynamic=True\n```\n\n### Detectron2\n\n```bash\n# Training\npython train_net.py --config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml \\\n    --num-gpus 1 OUTPUT_DIR ./output\n\n# Evaluation\npython train_net.py --config-file configs/faster_rcnn.yaml --eval-only \\\n    MODEL.WEIGHTS output/model_final.pth\n\n# Inference\npython demo.py --config-file configs/faster_rcnn.yaml \\\n    --input images/*.jpg --output results/ \\\n    --opts MODEL.WEIGHTS output/model_final.pth\n```\n\n### MMDetection\n\n```bash\n# Training\npython tools/train.py configs/faster_rcnn/faster-rcnn_r50_fpn_1x_coco.py\n\n# Testing\npython tools/test.py configs/faster_rcnn.py checkpoints/latest.pth --eval bbox\n\n# Inference\npython demo/image_demo.py demo.jpg configs/faster_rcnn.py checkpoints/latest.pth\n```\n\n### Model Optimization\n\n```bash\n# ONNX export and simplify\npython -c \"import torch; model = torch.load('model.pt'); torch.onnx.export(model, torch.randn(1,3,640,640), 'model.onnx', opset_version=17)\"\npython -m onnxsim model.onnx model_sim.onnx\n\n# TensorRT conversion\ntrtexec --onnx=model.onnx --saveEngine=model.engine --fp16 --workspace=4096\n\n# Benchmark\ntrtexec --loadEngine=model.engine --batch=1 --iterations=1000 --avgRuns=100\n```\n\n## Performance Targets\n\n| Metric | Real-time | High Accuracy | Edge |\n|--------|-----------|---------------|------|\n| FPS | >30 | >10 | >15 |\n| mAP@50 | >0.6 | >0.8 | >0.5 |\n| Latency P99 | <50ms | <150ms | <100ms |\n| GPU Memory | <4GB | <8GB | <2GB |\n| Model Size | <50MB | <200MB | <20MB |\n\n## Resources\n\n- **Architecture Guide**: `references/computer_vision_architectures.md`\n- **Optimization Guide**: `references/object_detection_optimization.md`\n- **Deployment Guide**: `references/production_vision_systems.md`\n- **Scripts**: `scripts/` directory for automation tools\n","readmeExcerpt":"--- name: senior-computer-vision description: 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 pipel","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Generate training configuration for YOLO or Faster R-CNN\npython scripts/vision_model_trainer.py models/ --task detection --arch yolov8\n\n# Analyze model for optimization opportunities (quantization, pruning)\npython scripts/inference_optimizer.py model.pt --target onnx --benchmark\n\n# Build dataset pipeline with augmentations\npython scripts/dataset_pipeline_builder.py images/ --format coco --augment"},{"language":"text","snippet":"Detection Requirements Analysis:\n- Target objects: [list specific classes to detect]\n- Real-time requirement: [yes/no, target FPS]\n- Accuracy priority: [speed vs accuracy trade-off]\n- Deployment target: [cloud GPU, edge device, mobile]\n- Dataset size: [number of images, annotations per class]"},{"language":"bash","snippet":"# COCO format (recommended)\npython scripts/dataset_pipeline_builder.py data/images/ \\\n    --annotations data/labels/ \\\n    --format coco \\\n    --split 0.8 0.1 0.1 \\\n    --output data/coco/\n\n# Verify dataset\npython -c \"from pycocotools.coco import COCO; coco = COCO('data/coco/train.json'); print(f'Images: {len(coco.imgs)}, Categories: {len(coco.cats)}')\""},{"language":"bash","snippet":"# For Ultralytics YOLO\npython scripts/vision_model_trainer.py data/coco/ \\\n    --task detection \\\n    --arch yolov8m \\\n    --epochs 100 \\\n    --batch 16 \\\n    --imgsz 640 \\\n    --output configs/\n\n# For Detectron2\npython scripts/vision_model_trainer.py data/coco/ \\\n    --task detection \\\n    --arch faster_rcnn_R_50_FPN \\\n    --framework detectron2 \\\n    --output configs/"},{"language":"bash","snippet":"# Ultralytics training\nyolo detect train data=data.yaml model=yolov8m.pt epochs=100 imgsz=640\n\n# Detectron2 training\npython train_net.py --config-file configs/faster_rcnn.yaml --num-gpus 1\n\n# Validate on test set\nyolo detect val model=runs/detect/train/weights/best.pt data=data.yaml"},{"language":"bash","snippet":"# Measure current model performance\npython scripts/inference_optimizer.py model.pt \\\n    --benchmark \\\n    --input-size 640 640 \\\n    --batch-sizes 1 4 8 16 \\\n    --warmup 10 \\\n    --iterations 100"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"CLAWHUB","editorialOverview":"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. --- name: senior-computer-vision description: 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 pipel","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":423,"uniquenessScore":61,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:22:36.897Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}