网络层

Layer (type) Output Shape Param # Connected to

input_1 (InputLayer) (None, array(64), ar 0


conv2d_5 (Conv2D) (None, 62, 62, 16) 448 input_1[0][0]


conv2d_1 (Conv2D) (None, 62, 62, 32) 896 input_1[0][0]


batch_normalization_5 (BatchNor (None, 62, 62, 16) 64 conv2d_5[0][0]


batch_normalization_1 (BatchNor (None, 62, 62, 32) 128 conv2d_1[0][0]


activation_5 (Activation) (None, 62, 62, 16) 0 batch_normalization_5[0][0]


activation_1 (Activation) (None, 62, 62, 32) 0 batch_normalization_1[0][0]


max_pooling2d_1 (MaxPooling2D) (None, 31, 31, 16) 0 activation_5[0][0]


average_pooling2d_1 (AveragePoo (None, 31, 31, 32) 0 activation_1[0][0]


conv2d_6 (Conv2D) (None, 29, 29, 16) 2320 max_pooling2d_1[0][0]


conv2d_2 (Conv2D) (None, 29, 29, 32) 9248 average_pooling2d_1[0][0]


batch_normalization_6 (BatchNor (None, 29, 29, 16) 64 conv2d_6[0][0]


batch_normalization_2 (BatchNor (None, 29, 29, 32) 128 conv2d_2[0][0]


activation_6 (Activation) (None, 29, 29, 16) 0 batch_normalization_6[0][0]


activation_2 (Activation) (None, 29, 29, 32) 0 batch_normalization_2[0][0]


max_pooling2d_2 (MaxPooling2D) (None, 14, 14, 16) 0 activation_6[0][0]


average_pooling2d_2 (AveragePoo (None, 14, 14, 32) 0 activation_2[0][0]


conv2d_7 (Conv2D) (None, 12, 12, 16) 2320 max_pooling2d_2[0][0]


conv2d_3 (Conv2D) (None, 12, 12, 32) 9248 average_pooling2d_2[0][0]


batch_normalization_7 (BatchNor (None, 12, 12, 16) 64 conv2d_7[0][0]


batch_normalization_3 (BatchNor (None, 12, 12, 32) 128 conv2d_3[0][0]


activation_7 (Activation) (None, 12, 12, 16) 0 batch_normalization_7[0][0]


activation_3 (Activation) (None, 12, 12, 32) 0 batch_normalization_3[0][0]


max_pooling2d_3 (MaxPooling2D) (None, 6, 6, 16) 0 activation_7[0][0]


average_pooling2d_3 (AveragePoo (None, 6, 6, 32) 0 activation_3[0][0]


conv2d_8 (Conv2D) (None, 4, 4, 16) 2320 max_pooling2d_3[0][0]


conv2d_4 (Conv2D) (None, 4, 4, 32) 9248 average_pooling2d_3[0][0]


batch_normalization_8 (BatchNor (None, 4, 4, 16) 64 conv2d_8[0][0]


batch_normalization_4 (BatchNor (None, 4, 4, 32) 128 conv2d_4[0][0]


activation_8 (Activation) (None, 4, 4, 16) 0 batch_normalization_8[0][0]


activation_4 (Activation) (None, 4, 4, 32) 0 batch_normalization_4[0][0]


conv2d_11 (Conv2D) (None, 14, 14, 10) 170 max_pooling2d_2[0][0]


conv2d_12 (Conv2D) (None, 14, 14, 10) 330 average_pooling2d_2[0][0]


conv2d_13 (Conv2D) (None, 31, 31, 10) 170 max_pooling2d_1[0][0]


conv2d_14 (Conv2D) (None, 31, 31, 10) 330 average_pooling2d_1[0][0]


conv2d_9 (Conv2D) (None, 4, 4, 10) 170 activation_8[0][0]


conv2d_10 (Conv2D) (None, 4, 4, 10) 330 activation_4[0][0]


max_pooling2d_4 (MaxPooling2D) (None, 3, 3, 10) 0 conv2d_11[0][0]


average_pooling2d_4 (AveragePoo (None, 3, 3, 10) 0 conv2d_12[0][0]


max_pooling2d_5 (MaxPooling2D) (None, 3, 3, 10) 0 conv2d_13[0][0]


average_pooling2d_5 (AveragePoo (None, 3, 3, 10) 0 conv2d_14[0][0]


flatten_1 (Flatten) (None, 160) 0 conv2d_9[0][0]


flatten_2 (Flatten) (None, 160) 0 conv2d_10[0][0]


flatten_3 (Flatten) (None, 90) 0 max_pooling2d_4[0][0]


flatten_4 (Flatten) (None, 90) 0 average_pooling2d_4[0][0]


flatten_5 (Flatten) (None, 90) 0 max_pooling2d_5[0][0]


flatten_6 (Flatten) (None, 90) 0 average_pooling2d_5[0][0]


dropout_1 (Dropout) (None, 160) 0 flatten_1[0][0]


dropout_2 (Dropout) (None, 160) 0 flatten_2[0][0]


dropout_3 (Dropout) (None, 90) 0 flatten_3[0][0]


dropout_4 (Dropout) (None, 90) 0 flatten_4[0][0]


dropout_5 (Dropout) (None, 90) 0 flatten_5[0][0]


dropout_6 (Dropout) (None, 90) 0 flatten_6[0][0]


dense_1 (Dense) (None, 3) 483 dropout_1[0][0]


dense_2 (Dense) (None, 3) 483 dropout_2[0][0]


dense_4 (Dense) (None, 3) 273 dropout_3[0][0]


dense_5 (Dense) (None, 3) 273 dropout_4[0][0]


dense_7 (Dense) (None, 3) 273 dropout_5[0][0]


dense_8 (Dense) (None, 3) 273 dropout_6[0][0]


multiply_2 (Multiply) (None, 3) 0 dense_1[0][0]
dense_2[0][0]


multiply_4 (Multiply) (None, 3) 0 dense_4[0][0]
dense_5[0][0]


multiply_6 (Multiply) (None, 3) 0 dense_7[0][0]
dense_8[0][0]


dense_3 (Dense) (None, 6) 24 multiply_2[0][0]


dense_6 (Dense) (None, 6) 24 multiply_4[0][0]


dense_9 (Dense) (None, 6) 24 multiply_6[0][0]


multiply_1 (Multiply) (None, 160) 0 flatten_1[0][0]
flatten_2[0][0]


multiply_3 (Multiply) (None, 90) 0 flatten_3[0][0]
flatten_4[0][0]


multiply_5 (Multiply) (None, 90) 0 flatten_5[0][0]
flatten_6[0][0]


pred_age_stage1 (Dense) (None, 3) 21 dense_3[0][0]


pred_age_stage2 (Dense) (None, 3) 21 dense_6[0][0]


pred_age_stage3 (Dense) (None, 3) 21 dense_9[0][0]


delta_s1 (Dense) (None, 1) 161 multiply_1[0][0]


delta_s2 (Dense) (None, 1) 91 multiply_3[0][0]


delta_s3 (Dense) (None, 1) 91 multiply_5[0][0]


local_delta_stage1 (Dense) (None, 3) 21 dense_3[0][0]


local_delta_stage2 (Dense) (None, 3) 21 dense_6[0][0]


local_delta_stage3 (Dense) (None, 3) 21 dense_9[0][0]


pred_a (Lambda) (None, 1) 0 pred_age_stage1[0][0]
pred_age_stage2[0][0]
pred_age_stage3[0][0]
delta_s1[0][0]
delta_s2[0][0]
delta_s3[0][0]
local_delta_stage1[0][0]
local_delta_stage2[0][0]
local_delta_stage3[0][0]

Total params: 40,915
Trainable params: 40,531
Non-trainable params: 384


DEBUG:root:Saving model…

已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 大白 设计师:CSDN官方博客 返回首页