将作为一个功能restnet训练的模型的负载权重加载到restnet模型中,但使用多层结构构建

我使用的代码将resnet模型训练为非功能层;

 base_model = tf.keras.applications.ResNet50(include_top=False, weights=None, input_shape=(224, 224, 3))
    base_model.trainable = True
    
    inputs = Input((224, 224, 3))
    h = base_model(inputs, training=True)
    model = Model(inputs, projection_3)

当您调用summary时:

Layer (type)                Output Shape              Param #   
=================================================================
 input_image (InputLayer)    [(None, 256, 256, 3)]     0         
                                                                 
 resnet50 (Functional)       (None, 8, 8, 2048)        23587712  
                                                                 
=================================================================

现在,我需要将重量加载到多层结构的resnet中

Resmodel  = tf.keras.applications.ResNet50(input_tensor=inputs, weights=None, include_top=False)

然而,当装载重量时,我得到:

 model.load_weights(filename)

ValueError: Layer count mismatch when loading weights from file. Model expected 106 layers, found 4 saved layers.

它是同一个模型,只有一个功能模型(整个模型作为一个层),另一个分为多个层。如何在它们之间传递重量。