Update streamlit_app.py

streamlit_app.py

@@ -7,27 +7,11 @@ st.title('🍅 Simple Tomato Leaf Disease Classifier')
 
 @st.cache_resource
 def load_model():
-    # Define the same model architecture as in training
-    model = tf.keras.models.Sequential([
-        tf.keras.layers.Conv2D(32, (3, 3), input_shape=(128, 128, 3), activation='relu'),
-        tf.keras.layers.MaxPooling2D(pool_size=(2, 2)),
-        tf.keras.layers.Conv2D(16, (3, 3), activation='relu'),
-        tf.keras.layers.MaxPooling2D(pool_size=(2, 2)),
-        tf.keras.layers.Conv2D(8, (3, 3), activation='relu'),
-        tf.keras.layers.MaxPooling2D(pool_size=(2, 2)),
-        tf.keras.layers.Flatten(),
-        tf.keras.layers.Dense(128, activation='relu'),
-        tf.keras.layers.Dropout(0.5),
-        tf.keras.layers.Dense(10, activation='softmax')
-    ])
-
-    # Load only the weights (not the full saved model)
-    model.load_weights('100-epoch with regularization.h5')
-    return model
+    return tf.keras.models.load_model('100-epoch with regularization.h5')
 
 model = load_model()
 
-# Class labels
+# Class names (update if your classes are different)
 class_names = [
     'Tomato___Bacterial_spot',
     'Tomato___Early_blight',
@@ -51,4 +35,4 @@ if uploaded_file is not None:
     img_array = np.expand_dims(img_array, axis=0)
     preds = model.predict(img_array)
     pred_class = np.argmax(preds, axis=1)[0]
-    st.success(f'Predicted Class: {class_names[pred_class]}')
+    st.success(f'Predicted Class: {class_names[pred_class]}')