在形状不兼容的张量上重新调用

Question

我正在尝试通过以下代码在此处创建 CNN + 回归模型：

# Create the base model from the pre-trained model MobileNet V2
cnn_model = keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                            include_top=False,
                                            weights='imagenet')

# The Regression Model
regression_model = keras.Sequential([
                        keras.layers.Dense(64, activation='relu', 
                                            input_shape=cnn_model.output_shape),
                        keras.layers.Dense(64, activation='relu')
                    ])

prediction_layer = tf.keras.layers.Dense(1)

# Final Model
model = keras.Sequential([
            cnn_model,
            regression_model,
            prediction_layer
        ])

现在的问题是我收到以下警告：

WARNING:tensorflow:Model was constructed with shape Tensor("dense_12_input:0", shape=(None, None, 7, 7, 1280), dtype=float32) for input (None, None, 7, 7, 1280), but it was re-called on a Tensor with incompatible shape (None, 7, 7, 1280).

有谁知道为什么会出现此警告以及我如何应对它，除非它是无害的。

Answer 1

好像是在CNN解决了我的问题后加了一个flatten。因为我们想将一个展平的向量传递给全连接层。该模型应如下所示：

model = keras.Sequential([
            cnn_model, keras.layers.Flatten(),
            regression_model,
            prediction_layer
        ])

在形状不兼容的张量上重新调用

Re-called on a Tensor with incompatible shape

python

keras

tensorflow

tf.keras

tensorflow2.0