尝试使用张量流自定义回调获取中间层预测时出现“层未连接，无输入可返回”错误

Question

我正在尝试使用自定义回调在训练期间访问模型中间层的预测。以下实际代码的精简版本演示了该问题。

import tensorflow as tf
import numpy as np

class Model(tf.keras.Model):
    def __init__(self, input_shape=None, name="cus_model", **kwargs):
        super(Model, self).__init__(name=name, **kwargs)
        
    def build(self, input_shape):
        self.dense1 = tf.keras.layers.Dense(input_shape=input_shape, units=32)
        
    def call(self, input_tensor):
        return self.dense1(input_tensor)

class CustomCallback(tf.keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        get_output = tf.keras.backend.function(
            inputs = self.model.layers[0].input,
            outputs = self.model.layers[0].output
        )
        print("Layer output: ",get_output.outputs)

X = np.ones((8,16))
y = np.sum(X, axis=1)

model = Model()
model.compile(optimizer='adam',loss='mean_squared_error', metrics='accuracy')
model.fit(X,y, epochs=8, callbacks=[CustomCallback()])

回调是按照此答案中的建议编写的。出现以下错误：

<ipython-input-3-635fd53dbffc> in on_epoch_end(self, epoch, logs)
     12     def on_epoch_end(self, epoch, logs=None):
     13         get_output = tf.keras.backend.function(
---> 14             inputs = self.model.layers[0].input,
     15             outputs = self.model.layers[0].output
     16         )
.
.
AttributeError: Layer dense is not connected, no input to return.

这是什么原因造成的？如何解决呢？

Answer 1

self.layers[0].input由于同样的错误，我也无法得到，但也许你可以直接调用Model这样定义的函数：

class Model(tf.keras.Model):
    def __init__(self, input_shape=None, name="cus_model", **kwargs):
        super(Model, self).__init__(name=name, **kwargs)
        if not input_shape:
            input_shape = (10,)
        self.dense1 = tf.keras.layers.Dense(input_shape=input_shape, units=32)
        self.dev_dataset = np.ones((8,16))

    def call(self, input_tensor):
        return self.dense1(input_tensor)


class CustomCallback(tf.keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        self.model.call(self.model.dev_dataset)


X = np.ones((8,16))
y = np.sum(X, axis=1)

model = Model()
model.compile(optimizer='adam',loss='mean_squared_error', metrics='accuracy')
model.fit(X,y, epochs=1, callbacks=[CustomCallback()])