keras -- multi-loss

关注

转载最新推荐文章于 2026-08-01 21:15:08 发布 751 阅读 AI 写同款· GEO 优化 ›

特征融合已经烂大街了？特征融合做好了仍然能发顶会顶刊！ 2025年了，都说做特征融合已经做的烂大街了，但事实上随着信息收集能力越来越完善，数据的模态维度只会越来越高，对数据特征融合的要求也只会越来越严格，我整理的。阅读详情

# create the base pre-trained model
input_tensor = Input(shape=(299, 299, 3))
base_model = Xception(include_top=True, weights='imagenet', input_tensor=None, input_shape=None)
plot_model(base_model, to_file='xception_model.png')
base_model.layers.pop()
base_model.outputs = [base_model.layers[-1].output]
base_model.layers[-1].outbound_nodes = []
base_model.output_layers = [base_model.layers[-1]]

feature = base_model
img1 = Input(shape=(299, 299, 3), name='img_1')
img2 = Input(shape=(299, 299, 3), name='img_2')

feature1 = feature(img1)
feature2 = feature(img2)

# Three loss functions
category_predict1 = Dense(100, activation='softmax', name='ctg_out_1')(
    Dropout(0.5)(feature1)
)
category_predict2 = Dense(100, activation='softmax', name='ctg_out_2')(
    Dropout(0.5)(feature2)
)
dis = Lambda(eucl_dist, name='square')([feature1, feature2])
model = Model(inputs=[img1, img2], outputs=[category_predict1, category_predict2, judge])
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9),
              loss={
                  'ctg_out_1': 'categorical_crossentropy',
                  'ctg_out_2': 'categorical_crossentropy',
                  'bin_out': 'categorical_crossentropy'},
              loss_weights={
                  'ctg_out_1': 1.,
                  'ctg_out_2': 1.,
                  'bin_out': 0.5
              },
              metrics=['accuracy'])