Create app.py

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+import tensorflow as tf
+from tensorflow import keras
+import numpy as np
+import matplotlib.pyplot as plt
+
+# Function to build a simple neural network
+def build_model():
+    model = keras.Sequential([
+        keras.layers.Dense(32, activation='relu', input_shape=(X_train.shape[1],)),
+        keras.layers.Dense(16, activation='relu'),
+        keras.layers.Dense(1, activation='sigmoid')
+    ])
+    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
+    return model
+
+# Load a sample dataset
+@st.cache
+def load_data():
+    (X_train, y_train), (X_test, y_test) = keras.datasets.mnist.load_data()
+    X_train = X_train.reshape(-1, 28 * 28).astype("float32") / 255
+    X_test = X_test.reshape(-1, 28 * 28).astype("float32") / 255
+    y_train = (y_train == 1).astype("float32")  # Binary classification (1 vs non-1)
+    y_test = (y_test == 1).astype("float32")
+    return X_train, y_train, X_test, y_test
+
+# Streamlit UI
+st.title('TensorFlow Playground with Streamlit')
+st.write("This is a simple neural network app built with TensorFlow and Streamlit.")
+
+# Data loading
+X_train, y_train, X_test, y_test = load_data()
+
+# User input to modify the network
+hidden_layers = st.slider('Number of hidden layers:', 1, 5, 2)
+neurons_per_layer = st.slider('Number of neurons per layer:', 8, 128, 32)
+
+# Build and compile the model
+model = keras.Sequential()
+model.add(keras.layers.Dense(neurons_per_layer, activation='relu', input_shape=(X_train.shape[1],)))
+for _ in range(hidden_layers - 1):
+    model.add(keras.layers.Dense(neurons_per_layer, activation='relu'))
+model.add(keras.layers.Dense(1, activation='sigmoid'))
+model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
+
+# Training
+st.write('Training model...')
+history = model.fit(X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test))
+
+# Model performance
+st.write("Training and validation accuracy:")
+fig, ax = plt.subplots()
+ax.plot(history.history['accuracy'], label='accuracy')
+ax.plot(history.history['val_accuracy'], label = 'val_accuracy')
+ax.set_xlabel('Epoch')
+ax.set_ylabel('Accuracy')
+ax.legend(loc='lower right')
+st.pyplot(fig)
+
+# Show final accuracy
+final_accuracy = history.history['accuracy'][-1]
+st.write(f"Final Training Accuracy: {final_accuracy:.2f}")