Question

我正在使用Keras功能API创建一个神经网络，该网络将单词嵌入层作为句子分类任务的输入。但是我的代码在连接输入层和嵌入层的开头就中断了。遵循https://medium.com/tensorflow/predicting-the-price-of-wine-with-the-keras-functional-api-and-tensorflow-a95d1c2c1b03上的教程之后，我的代码如下：

max_seq_length=100 #i.e., sentence has a max of 100 words 
word_weight_matrix = ... #this has a shape of 9825, 300, i.e., the vocabulary has 9825 words and each is a 300 dimension vector 
deep_inputs = Input(shape=(max_seq_length,))
embedding = Embedding(9825, 300, input_length=max_seq_length,
                          weights=word_weight_matrix, trainable=False)(deep_inputs) # line A
hidden = Dense(targets, activation="softmax")(embedding)
model = Model(inputs=deep_inputs, outputs=hidden)

然后A行会导致以下错误：

ValueError: You called `set_weights(weights)` on layer "embedding_1" with a  weight list of length 9825, but the layer was expecting 1 weights. Provided weights: [[-0.04057981  0.05743935  0.0109863  ...,  0.0072...

我真的不明白错误是什么意思...

似乎输入层定义不正确...以前，当我使用顺序模型并将嵌入层定义完全相同时，一切正常。但是当我切换到功能性API时，会出现此错误。

非常感谢任何帮助，在此先感谢

Answer 1

请尝试以下更新的代码：您必须在嵌入层中使用len(vocabulary) + 1！和weights=[word_weight_matrix]

max_seq_length=100 #i.e., sentence has a max of 100 words 
word_weight_matrix = ... #this has a shape of 9825, 300, i.e., the vocabulary has 9825 words and each is a 300 dimension vector 
deep_inputs = Input(shape=(max_seq_length,))
embedding = Embedding(9826, 300, input_length=max_seq_length,
                      weights=[word_weight_matrix], trainable=False)(deep_inputs) # line A
hidden = Dense(targets, activation="softmax")(embedding)
model = Model(inputs=deep_inputs, outputs=hidden)

Keras：功能性API输入层应用于嵌入层？

1 个答案: