Update app.py

app.py

@@ -8,17 +8,17 @@ import matplotlib.pyplot as plt
 # Streamlit UI
 st.title('Celsius to Fahrenheit Conversion with TensorFlow')
 
-# Define the model
+# Define the model with a different weight initializer
 model = tf.keras.Sequential([
-    tf.keras.layers.Dense(units=1, input_shape=[1])
+    tf.keras.layers.Dense(units=1, input_shape=[1], kernel_initializer='he_normal')
 ])
 
 # Set a suitable learning rate and number of epochs
 learning_rate = 0.01
 epochs = 500
 
-# Compile the model with the selected optimizer and loss function
-optimizer = tf.keras.optimizers.SGD(learning_rate=learning_rate)
+# Compile the model with the Adam optimizer and loss function
+optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
 model.compile(optimizer=optimizer, loss='mse')
 
 # Training data (Celsius to Fahrenheit)
@@ -31,8 +31,8 @@ input_celsius = st.number_input('Enter Celsius value:', value=0.0, format="%.1f"
 # Button to train the model and make prediction
 if st.button('Train Model and Predict Fahrenheit'):
     with st.spinner('Training...'):
-        # Fit the model with hardcoded hyperparameters
-        model.fit(celsius, fahrenheit, epochs=epochs)
+        # Fit the model
+        model.fit(celsius, fahrenheit, epochs=epochs, batch_size=4)
     st.success('Training completed!')
 
     # Make prediction