https://github.com/ankitsharma-tech/digit-recognize
A machine learning model for digit recognition.
https://github.com/ankitsharma-tech/digit-recognize
cnn-tensorflow tensorflow
Last synced: 8 months ago
JSON representation
A machine learning model for digit recognition.
- Host: GitHub
- URL: https://github.com/ankitsharma-tech/digit-recognize
- Owner: ankitsharma-tech
- License: mit
- Created: 2025-09-30T18:12:38.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-09-30T18:13:10.000Z (8 months ago)
- Last Synced: 2025-09-30T20:11:15.590Z (8 months ago)
- Topics: cnn-tensorflow, tensorflow
- Language: Python
- Homepage:
- Size: 2.73 MB
- Stars: 9
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 🖊️ Digit Recognizer Web App
🔗 **Live Demo:** [digit-recognize.onrender.com](https://digit-recognize.onrender.com)
A **Flask-based web application** that serves a **machine learning model** for **digit recognition**.
Configured for **production deployment** on **Render** with **Gunicorn**.
---
## ⚙️ Technologies
- **Backend:** Flask
- **Machine Learning:** TensorFlow
- **WSGI Server:** Gunicorn
- **Database Connector:** Psycopg2
- **Core Libraries:** NumPy, Matplotlib
---
## 📂 Project Structure
```
digit_recognize/
├── app.py # Main Flask app
├── requirements.txt # pip dependencies
├── render.yaml # Render deployment config
├── environment.yml # (Optional) Conda env file
├── run.sh # Local dev setup script
└── README.md # Project documentation
```
---
## 🚀 Running Locally
This project uses **uv** (fast Python installer), but works with any virtual environment.
1. **Clone the repository**
```bash
git clone https://github.com/ankitsharma-tech/Digit-Recognize.git
cd Digit-Recognize
```
2. **Create & activate a virtual environment**
```bash
# For Python 3.8
python3.8 -m venv .venv
source .venv/bin/activate
```
3. **Install dependencies**
```bash
pip install -r requirements.txt
```
4. **Start the app**
```bash
python app.py
```
App will be available at 👉 `http://0.0.0.0:5000`
---
## ☁️ Deployment on Render
This app is **deployment-ready** with `render.yaml`.
1. Push code to GitHub / GitLab / Bitbucket
2. In **Render Dashboard** → click **“New +” → “Web Service”**
3. Connect your repo
4. Render auto-detects `render.yaml` and applies:
- **Python:** `3.8.10`
- **Build Command:** `pip install -r requirements.txt`
- **Start Command:** `gunicorn app:app`
5. Click **“Create Web Service”** → live URL provided on success 🚀
---