vigorvision 2.1.5

Advanced AI vision and object detection framework by Vigor Industries Limited.

⚙️ VigorVision

VigorVision — an advanced, modular AI vision framework built by Vigor Industries Limited, designed for object detection, segmentation, and industry-specific visual intelligence.

---

🧭 Table of Contents

1. Overview
2. Features
3. Installation
4. Quick Start
5. Model Architecture
6. Configuration
7. Training
8. Visualization & Logging
9. Project Structure
10. Contributing
11. License
12. Contact

---

🧠 Overview

VigorVision provides a fully-featured, modular AI framework for vision applications such as:

• Industrial anomaly detection
• Object tracking and classification
• Manufacturing process vision systems
• Smart quality control and inspection

It leverages PyTorch, Albumentations, and Weights & Biases for maximum performance, extensibility, and interpretability.

---

✨ Features

Category	Highlights
🧩 Architecture	Modular design with customizable backbone, neck, and detection head
🧠 Training Engine	Optimized multi-threaded dataloaders with adaptive batch handling
🧮 Anchors	Auto-anchor analysis and smart anchor selection for detection models
📈 Visualization	Native support for TensorBoard and Weights & Biases (wandb)
🔧 Data Augmentation	Albumentations-based pipeline for advanced transformations
⚡ Performance	FP16 (mixed precision) and multi-GPU training support
🧰 Utilities	Built-in tools for dataset validation and metrics computation

---

⚙️ Installation

✅ From PyPI

pip install vigorvision
pip install torch>=2.0.0
pip install torchvision>=0.15.0
pip install albumentations>=1.3.0
pip install opencv-python>=4.8.0
pip install numpy>=1.24.0
pip install tqdm>=4.65.0
pip install pyyaml>=6.0
pip install tensorboard>=2.13.0
pip install wandb>=0.16.0
pip install scikit-learn>=1.3.0
pip install scipy>=1.11.0
pip install matplotlib>=3.8.0