|
Download README.md from funterpie/mnist-api: direct link, hf CLI and curl.
- Browser
- Download file 4.58 kB
-
https://huggingface.co/spaces/funterpie/mnist-api/resolve/main/README.md
- Command line
-
hf download hf://spaces/funterpie/mnist-api/README.md
-
curl -L -o README.md https://huggingface.co/spaces/funterpie/mnist-api/resolve/main/README.md
4.58 kB
π’ MNIST Digit Classifier
Handwritten digit recognition powered by a Keras Dense Neural Network β deployed via FastAPI on HuggingFace Spaces + Streamlit Cloud frontend.
π Live Demo
| Service | URL |
|---|---|
| π Streamlit Frontend | https://YOUR_APP.streamlit.app |
| β‘ FastAPI Backend | https://YOUR_HF_USERNAME-mnist-api.hf.space |
| π API Swagger Docs | https://YOUR_HF_USERNAME-mnist-api.hf.space/docs |
π Project Structure
mnist-digit-classifier/
β
βββ main.py # FastAPI backend
βββ app.py # Streamlit frontend
βββ Notebook.ipynb # Model training notebook
βββ mnist_model.keras # Trained Keras model
βββ Dockerfile # HuggingFace Docker config
βββ requirements.txt # Backend dependencies
βββ sample_digits/ # Sample test images (0β9)
β βββ digit_0.png
β βββ digit_1.png
β βββ ...
βββ README.md
π§ Model Architecture
Input Layer β 784 neurons (28Γ28 flattened)
Dense Layer 1 β 256 neurons, ReLU activation
Dense Layer 2 β 128 neurons, ReLU activation
Output Layer β 10 neurons, Softmax activation
| Parameter | Value |
|---|---|
| Dataset | MNIST (70,000 images) |
| Optimizer | Adam |
| Loss | Sparse Categorical Crossentropy |
| Epochs | 10 |
| Batch Size | 128 |
| Test Accuracy | 97.65% |
β‘ API Reference
Health Check
GET /
{
"message": "MNIST Digit Classifier API is running.",
"docs": "/docs"
}
Predict Digit
POST /predict/
Content-Type: multipart/form-data
Request: Upload any PNG/JPG image of a handwritten digit.
Response:
{
"filename": "digit_3.png",
"predicted_digit": 3,
"confidence": 0.9921,
"all_probabilities": {
"0": 0.0001, "1": 0.0000, "2": 0.0012,
"3": 0.9921, "4": 0.0003, "5": 0.0020,
"6": 0.0001, "7": 0.0002, "8": 0.0035, "9": 0.0005
}
}
cURL Example
curl -X POST "https://YOUR_HF_USERNAME-mnist-api.hf.space/predict/" \
-F "file=@digit_0.png"
π οΈ Local Setup
# 1. Clone the repo
git clone https://github.com/funterpie/mnist-digit-classifier.git
cd mnist-digit-classifier
# 2. Create virtual environment
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# 3. Install dependencies
pip install -r requirements.txt
# 4. Run FastAPI backend
uvicorn main:app --reload
# β http://127.0.0.1:8000/docs
# 5. Run Streamlit frontend (new terminal)
pip install streamlit
streamlit run app.py
# β http://localhost:8501
βοΈ Deployment Guide
FastAPI β HuggingFace Spaces (Docker)
- Go to huggingface.co/new-space
- Select Docker as SDK
- Push these files:
main.pymnist_model.kerasrequirements.txtDockerfileREADME.md
git clone https://huggingface.co/spaces/YOUR_HF_USERNAME/mnist-api
cd mnist-api
# copy your files here
git add . && git commit -m "deploy: FastAPI MNIST backend"
git push
Streamlit Frontend β Streamlit Cloud
- Push
app.py+requirements.txt+sample_digits/to GitHub - Go to share.streamlit.io
- Connect your GitHub repo
- Set main file:
app.py - Update
API_URLinapp.pyto your HF Space URL
π¨βπ» Author
Muhammad Taha Sattar Arain Founder & CEO β Alpha Orbit SMIT Batch 10 β AI & Data Science
Assignment 8 β Deep Learning | SMIT AI & Data Science Batch 10