다음과 같이 ResNet50 네트워크가 출력됩니다. ResNet50 네트워크는 유지하고, 여기에 추가 계층을 생성하여 사용할 예정입니다.
Model: "resnet50"
______________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
======================================================================================
input_1 (InputLayer) [(None, 224, 224, 3) 0
______________________________________________________________________________________
conv1_pad (ZeroPadding2D) (None, 230, 230, 3) 0 input_1[0][0]
______________________________________________________________________________________
conv1_conv (Conv2D) (None, 112, 112, 64) 9472 conv1_pad[0][0]
______________________________________________________________________________________
conv1_bn (BatchNormalization) (None, 112, 112, 64) 256 conv1_conv[0][0]
______________________________________________________________________________________
...(중간 생략)...
______________________________________________________________________________________
conv5_block3_out (Activation) (None, 7, 7, 2048) 0 conv5_block3_add[0][0]
______________________________________________________________________________________
avg_pool (GlobalAveragePooling2 (None, 2048) 0 conv5_block3_out[0][0]
______________________________________________________________________________________
predictions (Dense) (None, 1000) 2049000 avg_pool[0][0]
======================================================================================
Total params: 25,636,712
Trainable params: 25,583,592
Non-trainable params: 53,120
______________________________________________________________________________________