VGG
import tensorflow as tf # keras > cv
# tf.keras.applications.vgg16.VGG16
# tf.keras.applications.VGG16
vgg16 = tf.keras.applications.VGG16(include_top=True)
# vgg16 = tf.keras.applications.VGG16(include_top=False, input_shape=(400,400,3)) # Flatten 전까지만
# input_ = tf.keras.Input((400,400,3))
# vgg16 = tf.keras.applications.VGG16(include_top=False, input_tensor=input_)
vgg16.summary()
Model: "vgg16"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_7 (InputLayer) [(None, 224, 224, 3)] 0
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
flatten (Flatten) (None, 25088) 0
fc1 (Dense) (None, 4096) 102764544
fc2 (Dense) (None, 4096) 16781312
predictions (Dense) (None, 1000) 4097000
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
_________________________________________________________________
input_ = tf.keras.Input((224,224,3))
x = tf.keras.layers.Conv2D(64, 3, padding='same', activation='relu', name='block1_conv1')(input_)
x = tf.keras.layers.Conv2D(64, 3, padding='same', activation='relu', name='block1_conv2')(x)
x = tf.keras.layers.MaxPool2D(2,2,name='block1_pool')(x)
x = tf.keras.layers.Conv2D(128, 3, padding='same', activation='relu', name='block2_conv1')(x)
x = tf.keras.layers.Conv2D(128, 3, padding='same', activation='relu', name='block2_conv2')(x)
x = tf.keras.layers.MaxPool2D(2, 2,name='block2_pool')(x)
x = tf.keras.layers.Conv2D(256, 3, padding='same', activation='relu', name='block3_conv1')(x)
x = tf.keras.layers.Conv2D(256, 3, padding='same', activation='relu', name='block3_conv2')(x)
x = tf.keras.layers.Conv2D(256, 3, padding='same', activation='relu', name='block3_conv3')(x)
x = tf.keras.layers.MaxPool2D(2, 2,name='block3_pool')(x)
x = tf.keras.layers.Conv2D(512, 3, padding='same', activation='relu', name='block4_conv1')(x)
x = tf.keras.layers.Conv2D(512, 3, padding='same', activation='relu', name='block4_conv2')(x)
x = tf.keras.layers.Conv2D(512, 3, padding='same', activation='relu', name='block4_conv3')(x)
x = tf.keras.layers.MaxPool2D(2, 2,name='block4_pool')(x)
x = tf.keras.layers.Conv2D(512, 3, padding='same', activation='relu', name='block5_conv1')(x)
x = tf.keras.layers.Conv2D(512, 3, padding='same', activation='relu', name='block5_conv2')(x)
x = tf.keras.layers.Conv2D(512, 3, padding='same', activation='relu', name='block5_conv3')(x)
x = tf.keras.layers.MaxPool2D(2, 2,name='block5_pool')(x)
x = tf.keras.layers.Flatten()(x)
x = tf.keras.layers.Dense(4096, name='fc1')(x)
x = tf.keras.layers.Dense(4096, name='fc2')(x)
x = tf.keras.layers.Dense(1000, activation='softmax', name='predictions')(x)
model = tf.keras.Model(input_, x)
model.summary()
Model: "model_14"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 224, 224, 3)] 0
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
flatten_5 (Flatten) (None, 25088) 0
fc1 (Dense) (None, 4096) 102764544
fc2 (Dense) (None, 4096) 16781312
predictions (Dense) (None, 1000) 4097000
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
_________________________________________________________________
