如何在Tensorflow 2.0 RNN中使用预训练的嵌入矩阵作为嵌入层中的初始权重? [英] How to use a pre-trained embedding matrix in tensorflow 2.0 RNN as initial weights in an embedding layer?
问题描述
我想使用预训练的GloVe嵌入作为RNN编码器/解码器中嵌入层的初始权重.该代码在Tensorflow 2.0中.只需将嵌入矩阵作为权重= [embedding_matrix]参数添加到tf.keras.layers.Embedding层就不会这样做,因为编码器是一个对象,我现在不确定现在将embedding_matrix有效地传递给此对象训练时间.
I'd like to use a pretrained GloVe embedding as the initial weights for an embedding layer in an RNN encoder/decoder. The code is in Tensorflow 2.0. Simply adding the embedding matrix as a weights = [embedding_matrix] parameter to the tf.keras.layers.Embedding layer won't do it because the encoder is an object and I'm not sure now to effectively pass the embedding_matrix to this object at training time.
我的代码紧紧遵循Tensorflow 2.0文档中的神经机器翻译示例.在此示例中,如何将预训练的嵌入矩阵添加到编码器?编码器是一个对象.当我开始培训时,Tensorflow图无法使用GloVe嵌入矩阵.我收到错误消息:
My code closely follows the neural machine translation example in the Tensorflow 2.0 documentation. How would I add a pre-trained embedding matrix to the encoder in this example? The encoder is an object. When I get to training, the GloVe embedding matrix is unavailable to the Tensorflow graph. I get the error message:
RuntimeError:无法在Tensorflow图函数中获取值.
RuntimeError: Cannot get value inside Tensorflow graph function.
代码在训练过程中使用GradientTape方法和教师强制.
The code uses the GradientTape method and teacher forcing in the training process.
我尝试修改编码器对象,以在各个点上包括embedding_matrix,包括在编码器的 init ,call和initialize_hidden_state中.所有这些都失败了.关于stackoverflow和其他地方的其他问题是针对Keras或更旧版本的Tensorflow,而不是Tensorflow 2.0.
I've tried modifying the encoder object to include the embedding_matrix at various points, including in the encoder's init, call and initialize_hidden_state. All of these fail. The other questions on stackoverflow and elsewhere are for Keras or older versions of Tensorflow, not Tensorflow 2.0.
class Encoder(tf.keras.Model):
def __init__(self, vocab_size, embedding_dim, enc_units, batch_sz):
super(Encoder, self).__init__()
self.batch_sz = batch_sz
self.enc_units = enc_units
self.embedding = tf.keras.layers.Embedding(vocab_size, embedding_dim, weights=[embedding_matrix])
self.gru = tf.keras.layers.GRU(self.enc_units,
return_sequences=True,
return_state=True,
recurrent_initializer='glorot_uniform')
def call(self, x, hidden):
x = self.embedding(x)
output, state = self.gru(x, initial_state = hidden)
return output, state
def initialize_hidden_state(self):
return tf.zeros((self.batch_sz, self.enc_units))
encoder = Encoder(vocab_inp_size, embedding_dim, units, BATCH_SIZE)
# sample input
sample_hidden = encoder.initialize_hidden_state()
sample_output, sample_hidden = encoder(example_input_batch, sample_hidden)
print ('Encoder output shape: (batch size, sequence length, units) {}'.format(sample_output.shape))
print ('Encoder Hidden state shape: (batch size, units) {}'.format(sample_hidden.shape))
# ... Bahdanau Attention, Decoder layers, and train_step defined, see link to full tensorflow code above ...
# Relevant training code
EPOCHS = 10
training_record = pd.DataFrame(columns = ['epoch', 'training_loss', 'validation_loss', 'epoch_time'])
for epoch in range(EPOCHS):
template = 'Epoch {}/{}'
print(template.format(epoch +1,
EPOCHS))
start = time.time()
enc_hidden = encoder.initialize_hidden_state()
total_loss = 0
total_val_loss = 0
for (batch, (inp, targ)) in enumerate(dataset.take(steps_per_epoch)):
batch_loss = train_step(inp, targ, enc_hidden)
total_loss += batch_loss
if batch % 100 == 0:
template = 'batch {} ============== train_loss: {}'
print(template.format(batch +1,
round(batch_loss.numpy(),4)))
推荐答案
我试图做同样的事情并得到完全相同的错误.问题在于嵌入层中的权重当前已被弃用.将weights=
更改为embeddings_initializer=
对我有用.
I was trying to do the same thing and getting the exact same error. The problem was that weights in the Embedding layer is currently deprecated. Changing weights=
to embeddings_initializer=
worked for me.
self.embedding = tf.keras.layers.Embedding(vocab_size, embedding_dim,
embeddings_initializer=tf.keras.initializers.Constant(embedding_matrix),
trainable=False)
这篇关于如何在Tensorflow 2.0 RNN中使用预训练的嵌入矩阵作为嵌入层中的初始权重?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!