Keras Sequential 顺序模型（五）

最新推荐文章于 2024-05-14 13:31:54 发布

zlinzju

最新推荐文章于 2024-05-14 13:31:54 发布

阅读量945

点赞数 1

CC 4.0 BY-SA版权

分类专栏： Python # Keras

本文链接：https://blog.youkuaiyun.com/weixin_43026262/article/details/96596027

本文介绍了如何使用 Keras Sequential API 构建 LSTM 顺序模型解决回归问题，通过实例展示了RNN LSTM Regressor在预测sin(x)对应的cos(x)曲线中的应用。详细讨论了RNN的弊端，LSTM如何克服这些问题，以及LSTM的输入、输出和遗忘门的控制机制，提供了一个直观的理解。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

文章目录

案例：RNN LSTM Regressor

#RNN LSTM Regressor example

import numpy as np
np.random.seed(1337)  # for reproducibility
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import LSTM, TimeDistributed, Dense
from keras.optimizers import Adam

BATCH_START = 0
TIME_STEPS = 20
BATCH_SIZE = 50
INPUT_SIZE = 1
OUTPUT_SIZE = 1
CELL_SIZE = 20
LR = 0.006

def get_batch():
    global BATCH_START, TIME_STEPS
    # xs shape (50batch, 20steps)
    xs = np.arange(BATCH_START, BATCH_START+TIME_STEPS*BATCH_SIZE).reshape((BATCH_SIZE, TIME_STEPS)) / (10*np.pi)
    seq = np.sin(xs)
    res = np.cos(xs)
    BATCH_START += TIME_STEPS
    # plt.plot(xs[0, :], res[0, :], 'r', xs[0, :], seq[0, :], 'b--')
    # plt.show()
    return [seq[:, :, np.newaxis], res[:, :, np.newaxis], xs]

model = Sequential()
# build a LSTM RNN</