6
我试图将预训练的word2vec向量注入到现有的tensorflow seq2seq模型中。将预先训练的word2vec向量注入到TensorFlow中seq2seq
正在关注this answer,我制作了下面的代码。但它似乎并没有像应该那样提高性能,尽管变量中的值被更新了。
在我的理解中,错误可能是由于EmbeddingWrapper或embedding_attention_decoder独立于词汇顺序创建嵌入的事实?
将预训练载体加载到tensorflow模型中的最佳方法是什么?
SOURCE_EMBEDDING_KEY = "embedding_attention_seq2seq/RNN/EmbeddingWrapper/embedding"
TARGET_EMBEDDING_KEY = "embedding_attention_seq2seq/embedding_attention_decoder/embedding"
def inject_pretrained_word2vec(session, word2vec_path, input_size, dict_dir, source_vocab_size, target_vocab_size):
word2vec_model = word2vec.load(word2vec_path, encoding="latin-1")
print("w2v model created!")
session.run(tf.initialize_all_variables())
assign_w2v_pretrained_vectors(session, word2vec_model, SOURCE_EMBEDDING_KEY, source_vocab_path, source_vocab_size)
assign_w2v_pretrained_vectors(session, word2vec_model, TARGET_EMBEDDING_KEY, target_vocab_path, target_vocab_size)
def assign_w2v_pretrained_vectors(session, word2vec_model, embedding_key, vocab_path, vocab_size):
vectors_variable = [v for v in tf.trainable_variables() if embedding_key in v.name]
if len(vectors_variable) != 1:
print("Word vector variable not found or too many. key: " + embedding_key)
print("Existing embedding trainable variables:")
print([v.name for v in tf.trainable_variables() if "embedding" in v.name])
sys.exit(1)
vectors_variable = vectors_variable[0]
vectors = vectors_variable.eval()
with gfile.GFile(vocab_path, mode="r") as vocab_file:
counter = 0
while counter < vocab_size:
vocab_w = vocab_file.readline().replace("\n", "")
# for each word in vocabulary check if w2v vector exist and inject.
# otherwise dont change the value.
if word2vec_model.__contains__(vocab_w):
w2w_word_vector = word2vec_model.get_vector(vocab_w)
vectors[counter] = w2w_word_vector
counter += 1
session.run([vectors_variable.initializer],
{vectors_variable.initializer.inputs[1]: vectors})