| <!DOCTYPE html> |
| <html lang="en"> |
| <head> |
| <meta charset="UTF-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>HyperVision — Object Detection</title> |
| <style> |
| :root { |
| --bg: #0f1117; |
| --surface: #1a1d27; |
| --surface-2: #242836; |
| --border: #2e3345; |
| --text: #e4e6f0; |
| --text-dim: #8b90a5; |
| --accent: #6c5ce7; |
| --accent-hover: #7c6ef7; |
| --radius: 12px; |
| --font: 'Segoe UI', system-ui, -apple-system, sans-serif; |
| } |
| |
| * { margin: 0; padding: 0; box-sizing: border-box; } |
| |
| body { |
| font-family: var(--font); |
| background: var(--bg); |
| color: var(--text); |
| min-height: 100vh; |
| } |
| |
| |
| header { |
| background: var(--surface); |
| border-bottom: 1px solid var(--border); |
| padding: 20px 24px; |
| text-align: center; |
| } |
| |
| header h1 { |
| font-size: 28px; |
| font-weight: 700; |
| } |
| |
| header h1 span { color: var(--accent); } |
| |
| header .subtitle { |
| font-size: 14px; |
| color: var(--text-dim); |
| margin-top: 4px; |
| } |
| |
| header .subtitle a { |
| color: var(--accent); |
| text-decoration: none; |
| } |
| |
| |
| .container { |
| max-width: 1000px; |
| margin: 0 auto; |
| padding: 32px 24px; |
| } |
| |
| |
| .card { |
| background: var(--surface); |
| border: 1px solid var(--border); |
| border-radius: var(--radius); |
| padding: 24px; |
| margin-bottom: 24px; |
| } |
| |
| .card h2 { |
| font-size: 18px; |
| font-weight: 600; |
| margin-bottom: 16px; |
| display: flex; |
| align-items: center; |
| gap: 8px; |
| } |
| |
| .card p, .card li { |
| font-size: 14px; |
| line-height: 1.7; |
| color: var(--text-dim); |
| } |
| |
| .card ul { |
| padding-left: 20px; |
| } |
| |
| .card ul li { margin-bottom: 6px; } |
| |
| |
| .grid-2 { |
| display: grid; |
| grid-template-columns: 1fr 1fr; |
| gap: 24px; |
| } |
| |
| @media (max-width: 768px) { |
| .grid-2 { grid-template-columns: 1fr; } |
| } |
| |
| |
| .tags { |
| display: flex; |
| flex-wrap: wrap; |
| gap: 8px; |
| margin-top: 12px; |
| } |
| |
| .tag { |
| background: var(--surface-2); |
| border: 1px solid var(--border); |
| border-radius: 20px; |
| padding: 4px 12px; |
| font-size: 12px; |
| color: var(--text-dim); |
| } |
| |
| .tag.accent { |
| border-color: var(--accent); |
| color: var(--accent); |
| } |
| |
| |
| .btn { |
| display: inline-block; |
| background: var(--accent); |
| color: white; |
| padding: 10px 20px; |
| border-radius: 8px; |
| text-decoration: none; |
| font-size: 14px; |
| font-weight: 600; |
| transition: background 0.2s; |
| border: none; |
| cursor: pointer; |
| } |
| |
| .btn:hover { background: var(--accent-hover); } |
| .btn-outline { |
| background: transparent; |
| border: 1px solid var(--accent); |
| color: var(--accent); |
| } |
| .btn-outline:hover { background: var(--accent); color: white; } |
| |
| .btn-group { |
| display: flex; |
| gap: 12px; |
| flex-wrap: wrap; |
| margin-top: 16px; |
| } |
| |
| |
| .arch-table { |
| width: 100%; |
| border-collapse: collapse; |
| font-size: 13px; |
| } |
| |
| .arch-table td { |
| padding: 8px 12px; |
| border-bottom: 1px solid var(--border); |
| } |
| |
| .arch-table td:first-child { |
| font-weight: 600; |
| color: var(--accent); |
| width: 140px; |
| } |
| |
| |
| pre { |
| background: var(--bg); |
| border: 1px solid var(--border); |
| border-radius: 8px; |
| padding: 16px; |
| font-family: 'Cascadia Code', 'Fira Code', monospace; |
| font-size: 12px; |
| overflow-x: auto; |
| color: var(--text-dim); |
| line-height: 1.6; |
| } |
| |
| code { |
| background: var(--surface-2); |
| padding: 2px 6px; |
| border-radius: 4px; |
| font-size: 12px; |
| font-family: 'Cascadia Code', 'Fira Code', monospace; |
| } |
| |
| |
| footer { |
| background: var(--surface); |
| border-top: 1px solid var(--border); |
| padding: 16px 24px; |
| text-align: center; |
| font-size: 13px; |
| color: var(--text-dim); |
| } |
| |
| footer a { color: var(--accent); text-decoration: none; } |
| </style> |
| </head> |
| <body> |
| <header> |
| <h1>🔍 <span>HyperVision</span> — Object Detection</h1> |
| <div class="subtitle"> |
| Premium Edition by <a href="https://myndlabs.tech" target="_blank">Myndlabs.tech</a> |
| · Lightweight anchor-free object detection |
| </div> |
| </header> |
|
|
| <div class="container"> |
| |
| <div class="card"> |
| <h2>📋 Overview</h2> |
| <p> |
| HyperVision is a lightweight anchor-free object detection model, evolved from the |
| NanoDet-Plus architecture. It delivers real-time detection on mobile and edge devices |
| while maintaining competitive accuracy. The model uses Generalized Focal Loss with |
| a ShuffleNetV2 backbone and Ghost-PAN feature pyramid. |
| </p> |
| <div class="tags"> |
| <span class="tag accent">object-detection</span> |
| <span class="tag">computer-vision</span> |
| <span class="tag">lightweight</span> |
| <span class="tag">mobile</span> |
| <span class="tag">pytorch</span> |
| <span class="tag">ncnn</span> |
| <span class="tag">mnn</span> |
| <span class="tag">openvino</span> |
| <span class="tag">onnx</span> |
| </div> |
| <div class="btn-group"> |
| <a href="https://github.com/Yethikrishna/hypervision" target="_blank" class="btn">GitHub</a> |
| <a href="https://huggingface.co/Yethikrishna/Hypervision" target="_blank" class="btn btn-outline">Hugging Face</a> |
| <a href="https://myndlabs.tech" target="_blank" class="btn btn-outline">Myndlabs.tech</a> |
| </div> |
| </div> |
|
|
| |
| <div class="grid-2"> |
| <div class="card"> |
| <h2>🏗️ Architecture</h2> |
| <table class="arch-table"> |
| <tr><td>Type</td><td>Anchor-free one-stage detector (FCOS-style)</td></tr> |
| <tr><td>Loss</td><td>Generalized Focal Loss (QFL + DFL + GIoU)</td></tr> |
| <tr><td>Backbone</td><td>ShuffleNetV2 (configurable)</td></tr> |
| <tr><td>Neck</td><td>Ghost-PAN feature pyramid</td></tr> |
| <tr><td>Head</td><td>NanoDet-Plus head with AGM & DSLA</td></tr> |
| </table> |
| </div> |
|
|
| <div class="card"> |
| <h2>🚀 Deployment Backends</h2> |
| <table class="arch-table"> |
| <tr><td>ncnn</td><td>Mobile / Android C++</td></tr> |
| <tr><td>MNN</td><td>Mobile / Embedded C++</td></tr> |
| <tr><td>OpenVINO</td><td>Intel CPU / GPU</td></tr> |
| <tr><td>ONNX</td><td>Cross-platform</td></tr> |
| <tr><td>LibTorch</td><td>C++ inference</td></tr> |
| <tr><td>PyTorch</td><td>Python inference</td></tr> |
| </table> |
| </div> |
| </div> |
|
|
| |
| <div class="card"> |
| <h2>🧠 Supported Backbones</h2> |
| <p> |
| ShuffleNetV2, ResNet, MobileNetV2, EfficientNet-Lite, GhostNet, RepVGG, |
| Custom CSPNet, TIMM models |
| </p> |
| </div> |
|
|
| |
| <div class="card"> |
| <h2>🎯 Try It Yourself</h2> |
| <p> |
| To run inference with HyperVision, you can use the |
| <a href="https://github.com/Yethikrishna/hypervision" style="color: var(--accent);">GitHub repository</a> |
| or the Marimo notebook below. |
| </p> |
| <div class="btn-group"> |
| <a href="https://github.com/Yethikrishna/hypervision/blob/main/demo/demo-inference-with-pytorch.ipynb" target="_blank" class="btn">📓 Jupyter Notebook</a> |
| <a href="https://github.com/Yethikrishna/hypervision" target="_blank" class="btn btn-outline">💻 CLI Inference</a> |
| </div> |
| </div> |
|
|
| |
| <div class="card"> |
| <h2>📖 Citation</h2> |
| <pre>@misc{hypervision, |
| title={HyperVision: Lightweight anchor-free object detection model}, |
| author={Yethikrishna R}, |
| howpublished={\url{https://github.com/Yethikrishna/hypervision}}, |
| year={2025}, |
| note={Premium edition published by Myndlabs.tech} |
| }</pre> |
| </div> |
| </div> |
|
|
| <footer> |
| <a href="https://myndlabs.tech" target="_blank">Myndlabs.tech</a> — Enterprise-grade object detection solutions |
| </footer> |
| </body> |
| </html> |
