Update app.py

app.py

@@ -38,35 +38,35 @@ def classify_image(inp):
                                               class_mode='sparse')
 
 
-def design_model():
-    model = Sequential()
-    model.add(tf.keras.Input(shape=(256, 256, 1)))
+    def design_model():
+        model = Sequential()
+        model.add(tf.keras.Input(shape=(256, 256, 1)))
 
-    model.add(tf.keras.layers.Conv2D(2, 5, strides=3, activation="relu"))
-    model.add(tf.keras.layers.MaxPooling2D(pool_size=(5, 5), strides=(5,5)))
-    model.add(tf.keras.layers.Conv2D(4, 3, strides=1, activation="relu"))
-    model.add(tf.keras.layers.MaxPooling2D(pool_size=(3,2), strides=(2,2)))
+        model.add(tf.keras.layers.Conv2D(2, 5, strides=3, activation="relu"))
+        model.add(tf.keras.layers.MaxPooling2D(pool_size=(5, 5), strides=(5,5)))
+        model.add(tf.keras.layers.Conv2D(4, 3, strides=1, activation="relu"))
+        model.add(tf.keras.layers.MaxPooling2D(pool_size=(3,2), strides=(2,2)))
 
-    model.add(tf.keras.layers.Flatten())
+        model.add(tf.keras.layers.Flatten())
     #model.add(tf.keras.layers.Dense(8, activation="relu"))
     #model.add(tf.keras.layers.Dropout(.20))
-    model.add(tf.keras.layers.Dense(4, activation='softmax'))
+        model.add(tf.keras.layers.Dense(4, activation='softmax'))
 
-    model.summary()
+        model.summary()
 
-    callback = tf.keras.callbacks.EarlyStopping(monitor='accuracy', patience=5, restore_best_weights=True, verbose=1)
+        callback = tf.keras.callbacks.EarlyStopping(monitor='accuracy', patience=5, restore_best_weights=True, verbose=1)
 
-    print("Model designed")
-    return model, callback
+        print("Model designed")
+        return model, callback
 
 
-model, es_callback = design_model()
+    model, es_callback = design_model()
 
-model.compile(loss='sparse_categorical_crossentropy',
+    model.compile(loss='sparse_categorical_crossentropy',
               optimizer=keras.optimizers.Adam(learning_rate=0.01),
               metrics=['accuracy'])
 
-history = model.fit_generator(train_iterator,
+    history = model.fit_generator(train_iterator,
                               epochs=50,
                               steps_per_epoch=50,
                               validation_data=test_iterator,
@@ -74,12 +74,12 @@ history = model.fit_generator(train_iterator,
                               callbacks=[es_callback],
                               verbose=1)
 
-plt.plot(history.history['accuracy'])
-plt.title('model accuracy')
-plt.ylabel('accuracy')
-plt.xlabel('epoch')
-plt.legend(['train'], loc='upper left')
-plt.show()
+    plt.plot(history.history['accuracy'])
+    plt.title('model accuracy')
+    plt.ylabel('accuracy')
+    plt.xlabel('epoch')
+    plt.legend(['train'], loc='upper left')
+    plt.show()
 
 title = "Gradio Image Classifiction + Interpretation Example"
 gr.Interface(