Answer Happy

13. (10 points) Keras shows multiple layers of feature extraction using Python code. How is it identifying features? keras. Input (shape-(180, 180, 3)) x= data.augmentation (inputs) inputs x= layers. Rescaling (1-/255) (x) x = layers. Conv2D(filters-32, kernel.size-3, activation=" relu")(x) x = layers. MaxPooling2D(pool_size=2)(x) x = layers. Conv2D(filters-64, kernel-size-3, activation=" relu")(x) X= layers. MaxPooling2D(pool.size=2)(x) X = layers Conv2D(filters-128, kernel-size-3, activation=" relu")(x) x = layers. MaxPooling2D(pool_size=2)(x) x = layers. Conv2D( filters-256, kernel-size-3, activation-" relu" )(x) X= layers. MaxPooling2D(pool_size=2)(x) Xm layers. Conv2D( filters-256, kernel.size-3, activation="relu")(x) X = layers. Flatten ()(x)) x= layers. Dropout(0.5)(x) outputs layers. Dense (1, activation-"sigmoid")(x) model keras. Model (inputs-inputs, outputs-outputs) model compile(loss=" binary.crossentropy". optimizer="rmsprop", O shallow features, featuring engineering O local feature learning. global feature learning 3D tensors,