问题
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.
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: Cannot get value inside Tensorflow graph function.
The code uses the GradientTape method and teacher forcing in the training process.
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)))
回答1:
firslty : load pretrained embedding matrix using
def pretrained_embeddings(file_path, EMBEDDING_DIM, VOCAB_SIZE, word2idx):
# 1.load in pre-trained word vectors #feature vector for each word
print("graph in function",tf.get_default_graph())
print('Loading word vectors...')
word2vec = {}
with open(os.path.join(file_path+'.%sd.txt' % EMBEDDING_DIM), errors='ignore', encoding='utf8') as f:
# is just a space-separated text file in the format:
# word vec[0] vec[1] vec[2] ...
for line in f:
values = line.split()
word = values[0]
vec = np.asarray(values[1:], dtype='float32')
word2vec[word] = vec
print('Found %s word vectors.' % len(word2vec))
# 2.prepare embedding matrix
print('Filling pre-trained embeddings...')
num_words = VOCAB_SIZE
# initialization by zeros
embedding_matrix = np.zeros((num_words, EMBEDDING_DIM))
for word, i in word2idx.items():
if i < VOCAB_SIZE:
embedding_vector = word2vec.get(word)
if embedding_vector is not None:
# words not found in embedding index will be all zeros.
embedding_matrix[i] = embedding_vector
return embedding_matrix
2-then update Encoder class as following:
class Encoder(tf.keras.Model):
def __init__(self, vocab_size, embedding_dim, enc_units, batch_sz,embedding_matrix):
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))
3-calling function that loads pre-trained embedding to get embedding matrix
embedding_matrix = pretrained_embeddings(file_path, EMBEDDING_DIM,vocab_size, word2idx)
encoder = Encoder(vocab_inp_size, embedding_dim, units, BATCH_SIZE,embedding_matrix)
# 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))
Note : this works on tensorflow 1.13.1 well
回答2:
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)
来源：https://stackoverflow.com/questions/55770009/how-to-use-a-pre-trained-embedding-matrix-in-tensorflow-2-0-rnn-as-initial-weigh