Upload 3 files

Dockerfile

@@ -0,0 +1,23 @@
+FROM python:3.8-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    libglib2.0-0 \
+    libsm6 \
+    libxrender-dev \
+    libxext6 \
+    ffmpeg
+
+# Install Python dependencies
+COPY requirements.txt requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY . .
+
+# Expose port
+EXPOSE 7860
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,37 @@
+import gradio as gr 
+from sklearn.neural_network import MLPClassifier 
+import torchvision.datasets as datasets 
+import seaborn as sns 
+
+# Dark mode seaborn 
+sns.set_style("darkgrid")
+
+# Load MNIST data
+mnist_trainset = datasets.MNIST(root='./data', train=True, download=True, transform=None)
+mnist_testset = datasets.MNIST(root='./data', train=False, download=True, transform=None)
+
+X_train = mnist_trainset.data.numpy() 
+X_test = mnist_testset.data.numpy()
+y_train = mnist_trainset.targets.numpy()
+y_test = mnist_testset.targets.numpy()
+
+# Reshape and normalize data
+X_train = X_train.reshape(60000, 784) / 255.0
+X_test = X_test.reshape(10000, 784) / 255.0
+
+# Train the model
+mlp = MLPClassifier(hidden_layer_sizes=(32, 32))
+mlp.fit(X_train, y_train)
+
+# Print the accuracies 
+print("Training Accuracy: ", mlp.score(X_train, y_train))
+print("Testing Accuracy: ", mlp.score(X_test, y_test))
+
+# Define prediction function
+def predict(img):
+    img = img.reshape(1, 784) / 255.0
+    prediction = mlp.predict(img)[0]
+    return int(prediction)
+
+# Launch Gradio interface
+gr.Interface(fn=predict, inputs="sketchpad", outputs="label").launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+scikit-learn
+torchvision
+seaborn