2014sus VGG 연구 그룹에서 제안한 신경망 구조이다.
LeNet이나 AlexNet과 동일하지만 신경망의 층수가 더 많다.
VGG16은 층 16개로 구성되는데 합성곱층 13개 전결합층 3개이다.
합성곱층의 필터 크기가 3x3인데 AlexNet보다 더 세밀한 특징일 추출하기 위해서다.
VGG16 구조
https://www.kaggle.com/code/blurredmachine/vggnet-16-architecture-a-complete-guide
model = Sequential()
# first block
model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same',input_shape=(224,224, 3)))
model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))
# second block
model.add(Conv2D(filters=128, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(Conv2D(filters=128, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))
# third block
model.add(Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))
# forth block
model.add(Conv2D(filters=512, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(Conv2D(filters=512, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(Conv2D(filters=512, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))
# fifth block
model.add(Conv2D(filters=512, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(Conv2D(filters=512, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(Conv2D(filters=512, kernel_size=(3,3), strides=(1,1), activation='relu', padding='same'))
model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))
# sixth block (classifier)
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
model.summary()
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
conv2d_2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 112, 112, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
conv2d_4 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 56, 56, 128) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
conv2d_6 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
conv2d_7 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 28, 28, 256) 0
_________________________________________________________________
conv2d_8 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
conv2d_9 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
conv2d_10 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 14, 14, 512) 0
_________________________________________________________________
conv2d_11 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
conv2d_12 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
conv2d_13 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 7, 7, 512) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 25088) 0
_________________________________________________________________
dense_1 (Dense) (None, 4096) 102764544
_________________________________________________________________
dropout_1 (Dropout) (None, 4096) 0
_________________________________________________________________
dense_2 (Dense) (None, 4096) 16781312
_________________________________________________________________
dropout_2 (Dropout) (None, 4096) 0
_________________________________________________________________
dense_3 (Dense) (None, 1000) 4097000
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
_________________________________________________________________[참고자료]
https://www.hanbit.co.kr/store/books/look.php?p_code=B6566099029
