Keras_LSTM_Regression

最新推荐文章于 2024-01-07 00:01:48 发布

原创最新推荐文章于 2024-01-07 00:01:48 发布 · 550 阅读

0 ·

CC 4.0 BY-SA版权

Keras 专栏收录该内容

14 篇文章

订阅专栏

内容体现了学习时学一点忘一片的情况，反映出学习过程中遗忘带来的困扰。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

学一点，忘记一片，555~,

 

#!/usr/bin/env python
# -*- coding:utf-8 -*- 
# Author: Jia ShiLin

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
model.add(LSTM(
    batch_input_shape=(BATCH_SIZE, TIME_STEPS, INPUT_SIZE),
    output_dim=CELL_SIZE,
    return_sequences=True,  # 每一步都出，output at all steps   false:output at last step
    stateful=True,  # 批次之间的状态传递，True:the final state of batch1 is feed into the initial state of batch2

))

# add iy==output layer
model.add(TimeDistributed(Dense(OUTPUT_SIZE)))

# 自定义优化器
adam = Adam(LR)

# 编译
model.compile(
    optimizer=adam,
    loss='mse',
)

for step in range(501):
    # data shape = (batch_num, steps, inputs/outputs)
    X_batch, Y_batch, xs = get_batch()
    cost = model.train_on_batch(X_batch, Y_batch)
    pred = model.predict(X_batch, BATCH_SIZE)
    plt.plot(xs[0, :], Y_batch[0].flatten(), 'r', xs[0, :], pred.flatten()[:TIME_STEPS], 'b--')
    plt.ylim((-1.2, 1.2))
    plt.draw()
    plt.pause(0.1)
    if step % 10 == 0:
        print('train cost: ', cost)