资源简介
LSTM+CRF模型项包含完整代码LSTM+CRF模型项包含完整代码
代码片段和文件信息
from model.config import Config
from model.data_utils import CoNLLDataset get_vocabs UNK NUM \
get_glove_vocab write_vocab load_vocab get_char_vocab \
export_trimmed_glove_vectors get_processing_word
def main():
“““Procedure to build data
You MUST RUN this procedure. It iterates over the whole dataset (train
dev and test) and extract the vocabularies in terms of words tags and
characters. Having built the vocabularies it writes them in a file. The
writing of vocabulary in a file assigns an id (the line #) to each word.
It then extract the relevant GloVe vectors and stores them in a np array
such that the i-th entry corresponds to the i-th word in the vocabulary.
Args:
config: (instance of Config) has attributes like hyper-params...
“““
# get config and processing of words
config = Config(load=False)
processing_word = get_processing_word(lowercase=True)
# Generators
dev = CoNLLDataset(config.filename_dev processing_word)
test = CoNLLDataset(config.filename_test processing_word)
train = CoNLLDataset(config.filename_train processing_word)
# Build Word and Tag vocab
vocab_words vocab_tags = get_vocabs([train dev test])
vocab_glove = get_glove_vocab(config.filename_glove)
vocab = vocab_words & vocab_glove
vocab.add(UNK)
vocab.add(NUM)
# Save vocab
write_vocab(vocab config.filename_words)
write_vocab(vocab_tags config.filename_tags)
# Trim GloVe Vectors
vocab = load_vocab(config.filename_words)
export_trimmed_glove_vectors(vocab config.filename_glove
config.filename_trimmed config.dim_word)
# Build and save char vocab
train = CoNLLDataset(config.filename_train)
vocab_chars = get_char_vocab(train)
write_vocab(vocab_chars config.filename_chars)
if __name__ == “__main__“:
main()
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
目录 0 2018-12-20 03:16 LSTM+CRF_seq_tagging-master\
文件 51 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\.gitignore
文件 10762 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\LICENSE.txt
文件 2654 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\README.md
文件 1920 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\build_data.py
目录 0 2018-12-20 03:16 LSTM+CRF_seq_tagging-master\data\
文件 819 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\data\test.txt
文件 2141 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\evaluate.py
文件 202 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\makefile
目录 0 2018-12-20 03:16 LSTM+CRF_seq_tagging-master\model\
文件 0 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\model\__init__.py
文件 4828 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\model\ba
文件 3321 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\model\config.py
文件 11676 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\model\data_utils.py
文件 4682 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\model\general_utils.py
文件 13429 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\model\ner_model.py
文件 30 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\requirements.txt
文件 753 2017-11-09 03:14 LSTM+CRF_seq_tagging-master\train.py
- 上一篇:designv2.circ
- 下一篇:用于通信的4PPM编码verilog代码
相关资源
- 长短时记忆神经网络LSTM介绍及公式推
- 深度神经网络LSTM序列分类应用
- 基于TensorFlow实现的以多维特征输入的
- CRF++工具包使用介绍.ppt
- 条件随机场代码图像分割
- CRF 分词算法
- CoNLL 2000
- 深度学习实战项目-利用RNN与LSTM网络原
- CRF++windows版本
- 百度LSTM建模与CTC训练_贾磊
- lstm-char-cnn 基于CNN的LSTM语言模型.zip
- lstm神经网络(LSTMshili.ipynb)
- 神经网络LSTM 时间预测.rar
- windows版CRF++-0.58.zip;linux版CRF++-0.54.
- 基于crf的中文命名实体识别完整代码
- 条件随机场CRF图像处理工具
- lstm的源码
- 爱立信PCRF配置说明-全
- LSTM+CRF模型项目完整代码
- 数据集—基于TF NMT利用带有Attention的
- 数据集——基于TF NMT利用带有Attenti
- LSTM反向传播代码实现通过tensorflow和自
- LSTM公式推导详细解答
评论
共有 条评论