Update app.py

app.py

@@ -8,15 +8,17 @@ import matplotlib.pyplot as plt
 # Streamlit UI
 st.title('Celsius to Fahrenheit Conversion with TensorFlow')
 
-# Define the model with initial weights set
+# Define the model
 model = tf.keras.Sequential([
-    tf.keras.layers.Dense(units=1, input_shape=[1], kernel_initializer='zeros', bias_initializer='zeros')
+    tf.keras.layers.Dense(units=1, input_shape=[1])
 ])
 
-# Set a smaller learning rate for the optimizer
-optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
+# Sidebar for hyperparameter tuning
+learning_rate = st.sidebar.slider('Learning Rate', 0.001, 0.1, 0.01)
+epochs = st.sidebar.slider('Epochs', 100, 1000, 500)
 
-# Compile the model with an optimizer and loss function
+# Compile the model with selected optimizer and loss function
+optimizer = tf.keras.optimizers.SGD(learning_rate=learning_rate)
 model.compile(optimizer=optimizer, loss='mse')
 
 # Training data (Celsius to Fahrenheit)
@@ -26,12 +28,10 @@ fahrenheit = np.array([-40, 14, 32, 46.4, 59, 71.6, 100.4], dtype=float)
 # User input for the Celsius value to predict Fahrenheit
 input_celsius = st.number_input('Enter Celsius value:', value=0.0, format="%.1f")
 
-# Train the model with a fixed number of epochs
-epochs = 100
-
 # Button to train the model and make prediction
 if st.button('Train Model and Predict Fahrenheit'):
     with st.spinner('Training...'):
+        # Fit the model with the user-defined hyperparameters
         model.fit(celsius, fahrenheit, epochs=epochs)
     st.success('Training completed!')