README.md

metadata

title: Stroke Classification
emoji: 🚀
colorFrom: red
colorTo: red
sdk: docker
app_port: 7860
tags:
  - streamlit
pinned: false
short_description: Streamlit template space
license: apache-2.0

🧠 Stroke Classification System

Status: Dependency-conflict-free Streamlit app for stroke classification.

🚀 Features

• Clean Dependencies: No version conflicts
• System Status Check: Visual indicators for all components
• Fast Loading: Optimized for Hugging Face Spaces
• Error Handling: Graceful fallbacks for missing dependencies
• Medical Interface: Professional design

📋 Usage

1. Upload your .h5 model file to the Files tab
2. Click "Load Model" in the app
3. Upload brain scan images for classification
4. View results with confidence scores

🔧 Technical

• Framework: Streamlit (conflict-free)
• ML: TensorFlow 2.13.0 with pinned dependencies
• Visualization: Matplotlib-based heatmaps
• Deployment: Optimized for HF Spaces

---

Version: Dependency-conflict-free release

And here's your updated Dockerfile to match the port:

```dockerfile type="code" file="Dockerfile"
FROM python:3.9-slim

WORKDIR /app

# Set environment variables for Streamlit
ENV HOME=/tmp
ENV STREAMLIT_SERVER_HEADLESS=true
ENV STREAMLIT_SERVER_ENABLE_CORS=false
ENV STREAMLIT_SERVER_ENABLE_XSRF_PROTECTION=false
ENV STREAMLIT_BROWSER_GATHER_USAGE_STATS=false
ENV STREAMLIT_GLOBAL_DEVELOPMENT_MODE=false

RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    software-properties-common \
    git \
    && rm -rf /var/lib/apt/lists/*

COPY requirements.txt ./
COPY src/ ./src/

RUN pip3 install -r requirements.txt

# Create streamlit config directory in the temporary home
RUN mkdir -p /tmp/.streamlit

EXPOSE 7860

HEALTHCHECK CMD curl --fail http://localhost:7860/_stcore/health

ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=7860", "--server.address=0.0.0.0"]