b80fb3bdcfeac64d91b7365be1196392e013dcb8,autokeras/generator.py,RandomConvClassifierGenerator,generate,#RandomConvClassifierGenerator#,80

Before Change

        model = Sequential()
        for i in range(conv_num):
            kernel_num = randint(10, 30)
            if i == 0:
                model.add(conv(kernel_num,
                               input_shape=self.input_shape,
                               kernel_size=filter_shape,
                               activation="relu",
                               padding="same"))
            else:
                model.add(conv(kernel_num,
                               kernel_size=filter_shape,
                               activation="relu",
                               padding="same"))
            if random() > 0.5:
                model.add(pool(pool_size=pool_shape, padding="same"))
            if random() > 0.5:
                model.add(Dropout(dropout_rate))

After Change

            output_tensor = Dense(node_num, activation="relu")(output_tensor)
            if random() > 0.5:
                output_tensor = Dropout(dropout_rate)(output_tensor)
        output_tensor = Dense(self.n_classes, activation="softmax")(output_tensor)
        model = Model(input_tensor, output_tensor)
        model.compile(loss="categorical_crossentropy",
                      optimizer=Adam(),
                      metrics=["accuracy"])

Instances