使用TensorFlow实现LSTM

使用TensorFlow实现LSTM

使用Cell实现

# 以Cell方式实现LSTM
# %%
import os

import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, losses, optimizers, Sequential

# 指定GPU
os.environ["CUDA_VISIBLE_DEVICES"] = "1"

tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')

batch_size = 128  # 批量大小
total_words = 10000  # 词汇表大小N_vocab
max_review_len = 80  # 句子最大长度s，大于的句子部分将截断，小于的将填充
embedding_len = 100  # 词向量特征长度f
# 加载IMDB数据集，此处的数据采用数字编码，一个数字代表一个单词
(x_train, y_train), (x_test, y_test) = keras.datasets.imdb.load_data(num_words=total_words)
print(x_train.shape, len(x_train[0]), y_train.shape)
print(x_test.shape, len(x_test[0]), y_test.shape)
# %%
print(x_train[0])
# %%
# 数字编码表
word_index = keras.datasets.imdb.get_word_index()
# for k,v in word_index.items():
#     print(k,v)
# %%
word_index = {k: (v + 3) for k, v in word_index.items()}
word_index["<PAD>"] = 0
word_index["<START>"] = 1
word_index["<UNK>"] = 2  # unknown
word_index["<UNUSED>"] = 3
# 翻转编码表
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])


def decode_review(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])


decode_review(x_train[8])

# %%

# x_train:[b, 80]
# x_test: [b, 80]
# 截断和填充句子，使得等长，此处长句子保留句子后面的部分，短句子在前面填充
x_train = keras.preprocessing.sequence.pad_s