Keras AttributeError：“功能”对象没有属性“形状”答案

【问题标题】：Keras AttributeError: 'Functional' object has no attribute 'shape'Keras AttributeError：“功能”对象没有属性“形状”
【发布时间】：2021-01-31 22:30:59
【问题描述】：

尝试将 Densenet121 功能块添加到模型中。我需要 Keras 模型以这种格式编写，而不是使用

model=Sequential() 
model.add()

方法函数有什么问题，build_img_encod

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-62-69dd207148e0> in <module>()
----> 1 x = build_img_encod()

3 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    164         spec.min_ndim is not None or
    165         spec.max_ndim is not None):
--> 166       if x.shape.ndims is None:
    167         raise ValueError('Input ' + str(input_index) + ' of layer ' +
    168                          layer_name + ' is incompatible with the layer: '

AttributeError: 'Functional' object has no attribute 'shape'

def build_img_encod( ):
    base_model = DenseNet121(input_shape=(150,150,3),
                                 include_top=False,
                                 weights='imagenet')
    for layer in base_model.layers:
            layer.trainable = False
    flatten = Flatten(name="flatten")(base_model)
    img_dense_encoder = Dense(1024, activation='relu',name="img_dense_encoder", kernel_regularizer=regularizers.l2(0.0001))(flatten)
    model = keras.models.Model(inputs=base_model, outputs = img_dense_encoder)
    return model

【问题讨论】：

标签： tensorflow keras deep-learning transfer-learning

【解决方案1】：

您收到该错误的原因是您需要提供base_model 的input_shape，而不是base_model。

替换此行：model = keras.models.Model(inputs=base_model, outputs = img_dense_encoder)

与：model = keras.models.Model(inputs=base_model.input, outputs = img_dense_encoder)

【讨论】：

【解决方案2】：

def build_img_encod( ):
    dense = DenseNet121(input_shape=(150,150,3),
                                 include_top=False,
                                 weights='imagenet')
    for layer in dense.layers:
            layer.trainable = False
    img_input = Input(shape=(150,150,3))
    base_model = dense(img_input)
    flatten = Flatten(name="flatten")(base_model)
    img_dense_encoder = Dense(1024, activation='relu',name="img_dense_encoder", kernel_regularizer=regularizers.l2(0.0001))(flatten)
    model = keras.models.Model(inputs=img_input, outputs = img_dense_encoder)
    return model

这行得通..

【讨论】：

如果您检查我的答案，则无需像在此答案中那样强制提供输入。
实际上，您以这种方式提供两次输入密集 = DenseNet121(input_shape=(150,150,3), include_top=False, weights='imagenet') for layer in dense.layers: layer.trainable = 假 img_input = 输入（形状=（150,150,3））