def __init__(self):
self.char_dict = wordDict() # 词典
self.char2vec = word2Vec() # 词向量 gensim
self.embedding = self.char2vec.get_embedding()
self._build_layers()
self.model_path = [
None, './models/new', './models/thirdSentence/', './models/new'
]
self.loss_path = [f'./result/loss/{i}_sentence' for i in range(4)]
self.attention_img_path = [f'./result/attention/']
def __init__(self):
self.char_dict = wordDict()
self._pron_dict = dict()
with open(_pinyin_path, 'r') as fin:
for line in fin.readlines():
toks = line.strip().split()
ch = chr(int(toks[0], 16))
if ch not in self.char_dict:
continue
self._pron_dict[ch] = []
for tok in toks[1:]:
self._pron_dict[ch].append((tok[:-1], int(tok[-1])))
def _gen_word2vec():
print("Generating word2vec model ...")
word_dict = wordDict()
poems = Poems()
poems = [poem[0] + poem[1] + poem[2] + poem[3] for poem in poems]
print(poems[1])
model = models.Word2Vec(poems, size=WORD_VEC_DIM, min_count=1) # 低频词比较多
embedding = uniform(-1.0, 1.0, [len(word_dict), WORD_VEC_DIM])
for i, ch in enumerate(word_dict):
if ch in model:
embedding[i, :] = model[ch]
np.save(word2vec_path, embedding)
def _gen_poems():
print("Parsing poems ...")
word_dict = wordDict()
with open(poems_path, 'w', encoding='utf-8') as fout:
for corpus in _corpus_list:
with open(os.path.join(raw_dir, corpus), 'r',
encoding='utf-8') as fin:
for line in fin.readlines():
sentences = split_sentences(line)
if len(sentences[0].split()) != 3:
continue
all_word_in_dict = True
for sentence in sentences:
sentence = sentence.strip().split()
for ch in sentence:
if word_dict.word2int(ch) < 0:
all_word_in_dict = False
break
if not all_word_in_dict:
break
if all_word_in_dict:
fout.write('|'.join(sentences) + '\n')
print("Finished parsing %s." % corpus)
from paths import save_dir
from pron_dict import PronDict
from random import random
from singleton import Singleton
from utils import WORD_VEC_DIM, NUM_OF_SENTENCES
import numpy as np
import os
import sys
import tensorflow.compat.v1 as tf
import time
import matplotlib.pyplot as plt
BATCH_SIZE = 128
NUM_UNITS = 128
LEN_PER_SENTENCE = 5
_model_path = os.path.join(save_dir, 'model')
WORD_DICT_SIZE = wordDict().__len__()
model_load_path = {
0: './models/pair',
1: './models/pair',
2: './models/pair',
3: './models/pair',
4: './models/pair',
}
model_save_path = {
0: './models/pair',
1: './models/sentence1',
2: './models/sentence2',
3: './models/sentence3',
4: './models/sentence4',
}
result_save_path = {
def __init__(self):
'''if not check_uptodate(word2vec_path):
_gen_word2vec()'''
self.embedding = np.load(word2vec_path)
self.word_dict = wordDict()
from plan import Planner
from generator_2021 import Generator
from typing import Set, List
import os
from word_vec2 import word2Vec
from word_dict import wordDict
os.environ["TF_CPP_MIN_LOG_LEVEL"] = '3'
# For testing purpose.
if __name__ == '__main__':
word_dict = wordDict()
word2vec = word2Vec()
generator = Generator()
i = 0
while True:
i += 1
hint: str = input("Type first sentence: ")
print(hint)
keywords = [i for i in list(hint) if word_dict.word2int(i) != -1]
keyword = keywords[0]
keywords = keywords[1:] + word2vec.similar_word_(
keywords[0], 5 - len(keywords))
keywords = [keyword] + [i for i in keywords if i != keyword]
print("Keywords: ", keywords)
keywords = [' '.join(list(i)) for i in keywords]
poem: List[str] = generator.generate_by_multiple_models(
keywords, 0, './result/demo', '', f'{i}')
output = ''.join(poem.split()).strip('^').replace('$', '\n')
print("Poem: \n", output)
with open("./result/demo/result.txt", 'a', encoding='utf-8') as f:
f.write("Input: " + hint + '\n')