в процессе

This commit is contained in:
acidmikk 2023-12-07 22:35:52 +04:00
parent bcc00fa6a5
commit 71b16e78b7
3 changed files with 16049 additions and 0 deletions

File diff suppressed because it is too large Load Diff

View File

View File

@ -0,0 +1,70 @@
import torch
import torch.nn as nn
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Embedding, LSTM, Dense
with open('69209.txt', "r") as file:
text = file.read()
# Предварительная обработка текста (в зависимости от вашей задачи)
# Создание словаря для отображения слов в индексы и обратно
tokenizer = tf.keras.preprocessing.text.Tokenizer()
tokenizer.fit_on_texts([text])
total_words = len(tokenizer.word_index) + 1
# Подготовка данных для обучения (в зависимости от вашей задачи)
input_sequences = []
for line in text.split('\n'):
token_list = tokenizer.texts_to_sequences([line])[0]
for i in range(1, len(token_list)):
n_gram_sequence = token_list[:i+1]
input_sequences.append(n_gram_sequence)
max_sequence_length = max([len(x) for x in input_sequences])
input_sequences = tf.keras.preprocessing.sequence.pad_sequences(input_sequences, maxlen=max_sequence_length, padding='pre')
X, y = input_sequences[:,:-1],input_sequences[:,-1]
y = tf.keras.utils.to_categorical(y, num_classes=total_words)
# Определение архитектуры модели
model = Sequential()
model.add(Embedding(total_words, 50, input_length=max_sequence_length-1))
model.add(LSTM(100))
model.add(Dense(total_words, activation='softmax'))
# Компиляция модели
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
# Обучение модели
model.fit(X, y, epochs=100, verbose=2)
# Генерация текста с использованием обученной модели
def generate_text(seed_text, next_words, model, max_sequence_length):
for _ in range(next_words):
token_list = tokenizer.texts_to_sequences([seed_text])[0]
token_list = tf.keras.preprocessing.sequence.pad_sequences([token_list], maxlen=max_sequence_length - 1,
padding='pre')
predicted = model.predict_classes(token_list, verbose=0)
output_word = ""
for word, index in tokenizer.word_index.items():
if index == predicted:
output_word = word
break
seed_text += " " + output_word
return seed_text
# Пример генерации текста (замените seed_text и next_words на свои значения)
seed_text = "your seed text here"
next_words = 50
generated_text = generate_text(seed_text, next_words, model, max_sequence_length)
print(generated_text)