Question

class Dense(layers.Layer):
    def __init__(self, units):
        super(Dense, self).__init__()
        self.units = units

    def build(self, input_shape):
        self.w = self.add_weight(
            name='w',
            shape=(input_shape[-1], self.units),
            initializer='random_normal',
            trainable=True,
        )
        self.b = self.add_weight(
            name='b',
            shape=(self.units,),
            initializer='zeros',
            trainable=True,
        )

        def call(self, inputs):
            return tf.matmul(inputs, self.w) + self.b

class MyRelu(layers.Layer):
    def __init__(self):
        super(MyRelu, self).__init__()

    def call(self, x):
        return tf.math.maximum(x, 0)

class MyModel(keras.Model):
    def __init__(self, num_classes=10):
        super(MyModel, self).__init__()
        self.dense1 = Dense(64)
        self.dense2 = Dense(num_classes)
        self.relu = MyRelu()

    def call(self, input_tensor):
        x = self.relu(self.dense1(input_tensor))
        return self.dense2(x)

model = MyModel()

model.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),  #from_logits is used cuz softmax isn't used in the output layer
    optimizer = keras.optimizers.Adam(),
    metrics=['accuracy'],
)

model.fit(X_train, y_train, batch_size=32, epochs=2, verbose=2)
#print(model.summary())
model.evaluate(X_test, y_test, batch_size=32, verbose=2)

这是我得到的错误：

ValueError: 没有为任何变量提供梯度：['my_model/dense/w:0', 'my_model/dense/b:0', 'my_model/dense_1/w:0', 'my_model/dense_1/b: 0']。

我似乎无法找到解决此错误的方法。我看过其他类似的错误，但没有运气。提前致谢！

ValueError：没有为张量流中的任何变量错误提供梯度

0 个答案: