我在InceptionResNetV2模型(预训练)之前添加了一个密集层,这是InceptionResNetV2输出
model_base = InceptionResNetV2(include_top=True, weights='imagenet')
x = model_base.get_layer('avg_pool').output
x = Dense(3, activation='softmax')(x)这是要添加的图层
input1 = Input(shape=input_shape1)
pre1 = Conv2D(filters=3, kernel_size=(5, 5), padding='SAME',
input_shape=input_shape1, name='first_dense')(input1)
pre = Model(inputs=input1, outputs=pre1)这是两个模型的结合
after = Model(inputs=pre.output, outputs=x)
model = Model(inputs=input1, outputs=after.output)
model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])使用
pre.output作为
after.input但它不起作用。我怎么解决它呢?
https://stackoverflow.com/questions/47678108
复制相似问题