image_size 변환에서 질문있습니다.

마지막 파트에서 로직들을 함수화 해서 쓸 때

IMAGE_SIZE = 32

...

def do_cifar10_train_evaluation(image_size=IMAGE_SIZE, model_name='vgg16'):

과 같이 정의 하고

history, evaluation_result = do_cifar10_train_evaluation(image_size=64, model_name='xception')으로 사용하는데 위에 IMAGE_SIZE를 바꿔야 input_size가 바뀌는거 같은데 저만 그러나요...? 아니면 강의때 설명 해 주셨는데 제가 못들은걸까요...?

아래는 vgg16으로 IMAGE_SIZE를 직접 바꿨을 때랑 안바꿨을 때 summary 초반 부분입니다.

IMAGE_SIZE = 32
...

Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 32, 32, 3)]       0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 32, 32, 64)        1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 32, 32, 64)        36928     
_________________________________________________________________

IMAGE_SIZE = 64
...

Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 64, 64, 3)]       0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 64, 64, 64)        1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 64, 64, 64)        36928     

def create_model(model_name='vgg16', verbose=False):
    
    input_tensor = Input(shape=(IMAGE_SIZE, IMAGE_SIZE, 3))
    if model_name == 'vgg16':
        base_model = VGG16(input_tensor=input_tensor, include_top=False, weights='imagenet')
    elif model_name == 'resnet50':
        base_model = ResNet50V2(input_tensor=input_tensor, include_top=False, weights='imagenet')
    elif model_name == 'xception':
        base_model = Xception(input_tensor=input_tensor, include_top=False, weights='imagenet')