README.md

metadata

title: House Model Detaction
emoji: 🏃
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 5.25.2
app_file: app.py
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Architectural Floor Plan Analyzer

This Hugging Face Space allows users to upload PDF floor plans and get detailed room-level information in structured JSON format. The application uses Google's Gemini Pro Vision model to analyze the floor plans and extract structured data.

Features

• Upload PDF floor plans
• Extract images from PDFs
• Analyze floor plans using Gemini Pro Vision
• Get structured JSON output with room details
• Optional description field for additional context

Setup Instructions

1. Create a Hugging Face Space

1. Go to Hugging Face
2. Click on "Create new Space"
3. Select "Gradio" as the SDK
4. Choose a name for your Space (e.g., "floor-plan-analyzer")
5. Set Space visibility (Public or Private)
6. Create the Space

2. Add Environment Variables

You need to add your Gemini API key as an environment variable:

1. Go to your Space's settings
2. Click on "Repository secrets"
3. Add a new secret:
   • Name: GEMINI_API_KEY
   • Value: Your Gemini API key from Google AI Studio

3. Upload Files

Upload the following files to your Space:

• app.py (the main application)
• requirements.txt (dependencies)

You can do this through the Hugging Face web interface or by pushing to the git repository.

Usage

1. Open your Hugging Face Space
2. Upload a PDF floor plan
3. (Optional) Add a description with additional details
4. Click "Analyze Floor Plan"
5. View the extracted images and JSON output

JSON Output Format

The output is a structured JSON array with detailed room information:

[
  {
    "name": "Room name",
    "area_m2": 0.0,
    "position": "approximate location (e.g., north, south-east corner)",
    "dimensions_m": {
      "width": 0.0,
      "length": 0.0
    },
    "windows": 0,
    "window_positions": ["north wall", "east wall"],
    "doors": 0,
    "door_positions": ["interior", "to terrace"],
    "connected_rooms": ["Room A", "Room B"],
    "has_external_access": true,
    "ceiling_height_m": 2.4,
    "furniture": ["sofa", "kitchen island"],
    "estimated": false
  }
]

Limitations

• The quality of the analysis depends on the clarity and quality of the uploaded floor plan
• The application works best with clearly labeled floor plans
• Large or complex floor plans may take longer to process
• Gemini may need to estimate some values if they're not explicitly labeled in the plan

Troubleshooting

• If you encounter errors related to the API key, ensure the GEMINI_API_KEY environment variable is set correctly
• If the PDF fails to process, try converting it to a clearer format or using a different PDF
• For any other issues, check the error messages in the application output