Computer Vision Model Selection, Architecture Design & Training Strategy
Design Production-Ready Computer Vision Models Fast
What You Can Do
You'll gain structured workflows to architect computer vision models from scratch, optimize training pipelines for your hardware constraints, and debug common CV issues like vanishing gradients or poor data augmentation. This skill walks you through model selection (CNN, Vision Transformers, YOLO variants), training strategy design, and performance profiling — turning research papers into production-ready systems.
Features
Evaluate CNNs, Vision Transformers, EfficientNets, and specialized architectures (YOLO, Mask R-CNN) against your accuracy-latency tradeoffs
Profile data loaders, batch sizes, learning rates, and augmentation strategies to maximize GPU utilization and convergence speed
Diagnose vanishing gradients, underfitting, overfitting, and data quality issues with step-by-step decision trees and remediation strategies
Decision tree for choosing PyTorch vs TensorFlow vs JAX based on team expertise, deployment target, and research needs
Pre-built strategies for image classification, object detection, semantic segmentation, and multi-task CV workflows
Evaluate fine-tuning vs feature extraction vs domain adaptation based on dataset size and task similarity
Measure inference latency, memory footprint, accuracy on edge devices, and identify optimization bottlenecks
Verify model quantization, ONNX export, batch inference setup, and deployment target compatibility
Example Output
Example 1: Model Selection for Real-Time Object Detection
Input: "I need to detect cars in 1080p video at 30 FPS on an NVIDIA Jetson. Dataset is 50K labeled images."
Output:
Recommended: YOLOv8-nano (PyTorch)
- Inference: ~15ms per frame on Jetson (achieves 67 FPS target)
- Accuracy: mAP 0.37 (sufficient for tracking)
- Memory: 6.5MB (fits on-device)
- Alt: TensorFlow Lite MobileNet-SSD if iOS deployment needed
Training Strategy:
1. Start with pretrained YOLOv8-nano on COCO
2. Augmentation: Random hue/saturation shifts, horizontal flips, mosaic (for varied object scales)
3. Batch size: 64 on V100 (adjust if OOM)
4. Learning rate: 0.01 → 0.001 (cosine annealing over 100 epochs)
5. Validation: Split 10% of data, measure mAP every 10 epochs
Example 2: Debugging Vanishing Gradients
Symptom: Loss plateaus after 5 epochs, weights don't update.
Diagnosis Tree:
✓ Check gradient magnitude at each layer → gradients < 1e-7 in early layers?
✓ Add batch norm before activation functions
✓ Reduce learning rate (0.01 → 0.001) or use warm-up schedule
✓ Verify data normalization (images scaled to [-1, 1] or [0, 1]?)
✓ Switch activation: ReLU → Leaky ReLU for deeper networks
✓ Add skip connections (ResNet-style) if depth > 50 layers
Result: Adding batch norm + skip connections → loss resumes descent
What's Included
- SKILL.md: Complete CV model selection and training workflows with decision trees, validation checklists, and debugging playbooks
- Architecture comparison template: Side-by-side specs (latency, accuracy, memory) for 15+ model families
- Training configuration checklist: Data loading, augmentation, optimization, and hardware setup verification
- Debugging decision tree: Common CV failure modes and remediation strategies
- Framework selection guide: PyTorch vs TensorFlow vs JAX comparison matrix
- Data augmentation recipes: 8+ strategies (class-balanced, geometric, photometric, mixup variants)
- Performance profiling script template: Measure inference time and memory on target hardware
Who It's For
- ML Engineers building production computer vision systems from prototype to deployment
- Computer Vision Specialists designing custom architectures for novel applications
- Data Scientists scaling image classification, detection, or segmentation projects
- AI Product Managers evaluating model feasibility and resource requirements for new features
- Research Scientists transitioning academic models into robust, reproducible training pipelines
Best For
- Model architecture selection for new image classification, detection, or segmentation projects
- Training pipeline optimization to maximize accuracy within latency/memory constraints
- Debugging convergence issues when loss plateaus or gradients vanish
- Framework and library decisions when choosing PyTorch, TensorFlow, or other stacks
- Data augmentation strategy design to improve model robustness with limited data
- Edge device deployment planning for Jetson, mobile, or browser-based inference
- Transfer learning evaluations to decide between fine-tuning pretrained models vs training from scratch
You might also like
You can rapidly synthesize disparate urban site information—demographics, infrastructure, ecology, regulations, and spatial typologies—into explicit design frameworks. Claude helps you extract actionable insights that directly inform concept development, phasing strategies, and design interventions, bridging the gap between site investigation and design synthesis by creating clear connections between existing conditions and design opportunities.
by az9713
Diagnose and resolve computer vision model failures using a structured, multi-angle debugging framework. You'll systematically investigate root causes across model architecture, data quality, preprocessing, and inference stages—then receive targeted fixes to get your model back on track.
You can input earth retention system parameters—wall type, soil properties, loading conditions, and geometry—and Claude will perform comprehensive stability analysis including bearing capacity, sliding resistance, and overturning checks. The skill generates professional engineering reports with calculated factors of safety, design narratives, and permit-ready documentation that aligns with ASCE 7, ACI 318, and local building code requirements across gravity walls, cantilever walls, soldier pile systems, sheet pile walls, and MSE walls.
by az9713
You can systematically analyze raw XYZ survey coordinates to identify meaningful patterns, validate data quality, and detect surveying errors before they impact design phases. This skill helps you interpret slope gradients, drainage patterns, and terrain complexity while generating constraint reports that communicate site limitations to design teams. You'll produce professional topographic analyses that reveal drainage zones, stability issues, and access constraints invisible in raw measurements.
by az9713
You can submit architectural design documents, floor plans, and project parameters to receive a comprehensive compliance analysis that cross-references IBC, local amendments, zoning ordinances, and ADA accessibility requirements. Claude identifies specific gaps, cites applicable code sections, explains why each gap matters, and provides concrete remediation strategies—all before formal design review submission when corrections are costly and schedule-impacting.
by az9713
You can accelerate HVAC design workflows by inputting building parameters—envelope characteristics, occupancy data, climate conditions, and existing systems—and receiving calculated heating/cooling loads, equipment sizing recommendations, and zone-by-zone analysis. Claude organizes complex building data into actionable design parameters and specification summaries for client review, permit submission, and professional validation against ASHRAE and ACCA standards.
by az9713
This skill enables you to rapidly produce structural analyses for timber members, including bending, shear, compression, and combined stress calculations. You can determine lateral load capacity for shear walls, design connections, evaluate code compliance against NDS standards, assess serviceability limits, and generate calculation frameworks suitable for permit submission and engineer stamping.
by az9713
Design earth retention systems by inputting soil properties, site geometry, and regulatory requirements. Claude calculates lateral earth pressures using Coulomb, Rankine, and Mononobe-Okabe methods, verifies factors of safety for internal and external stability, compares competing retention concepts (gravity walls, cantilever, anchored, sheet-pile, soil-nail), and generates cost-benefit analysis and regulatory documentation packages ready for permit submission.
by az9713