我试图使用Keras自定义层实现论文中提到的图卷积层：GCNN。
当我尝试训练我的模型时，出现了以下错误：
Traceback (most recent call last):File "main.py", line 35, in <module>model.fit(train_images, train_labels, validation_data=(test_images, test_labels), epochs=50, batch_size=32)File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1010, in fitself._make_train_function()File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 509, in _make_train_functionloss=self.total_loss)File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 91, in wrapperreturn func(*args, **kwargs)File "/usr/local/lib/python2.7/dist-packages/keras/optimizers.py", line 256, in get_updatesgrads = self.get_gradients(loss, params)File "/usr/local/lib/python2.7/dist-packages/keras/optimizers.py", line 91, in get_gradientsraise ValueError('An operation has `None` for gradient. 'ValueError: An operation has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.我不知道如何解决这个问题。
有人能简要解释一下我应该做什么吗？
我已经查看了Keras官方文档关于编写自定义层的部分，但它没有具体说明这个问题。 链接
以下是我的自定义层的代码。
class GraphConvolutionalLayer(Layer):def __init__(self, A, num_input_features, num_output_features, **kwargs): self.A = A self.num_input_features = num_input_features self.num_output_features = num_output_features self.num_vertices = A.get_shape().as_list()[0] self.input_spec = (self.num_vertices, num_input_features) super(GraphConvolutionalLayer, self).__init__(**kwargs)def build(self, input_shape): self.k0 = self.add_weight(name='k0', shape=(self.num_output_features, self.num_input_features), initializer='uniform', trainable=True) self.k1 = self.add_weight(name='k1', shape=(self.num_output_features, self.num_input_features), initializer='uniform', trainable=True) self.H = tf.einsum('ab,cd->abcd', tf.convert_to_tensor(self.k0, dtype=tf.float32), tf.eye(self.num_vertices)) self.built = Truedef call(self, Vin): Vin2 = tf.reshape(tf.transpose(Vin, [0, 2, 1]), [Vin.get_shape().as_list()[1] * Vin.get_shape().as_list()[2], -1]) H_tmp = tf.reshape(tf.transpose(self.H, [0, 2, 1, 3]), [ self.num_output_features, self.num_vertices, self.num_vertices * self.num_input_features]) Vout = tf.transpose(K.dot(H_tmp, Vin2), [2, 1, 0]) return Voutdef compute_output_shape(self, input_shape): return (self.num_vertices, self.num_output_features)以下是主文件的代码。
main_input = Input(shape=train_images[0].shape)Vout1 = GraphConvolutionalLayer(A, 1, 4)(main_input)Vout2 = GraphConvolutionalLayer(A, 4, 8)(Vout1)Vout3 = Flatten()(Vout2)Vout4 = Dense(10, activation='sigmoid')(Vout3)print(train_images.shape, train_labels.shape)model = Model(inputs=main_input, outputs=Vout4)print(model.summary())model.compile(optimizer='rmsprop', loss='binary_crossentropy')model.fit(train_images, train_labels, validation_data=(test_images, test_labels), epochs=50, batch_size=32)回答：
在这里，我使用uniform作为初始化器。当我更改它时，我没有得到任何错误。我不知道为什么会这样，但通过更改那一行，我能够解决我的错误。
