- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者:K同学啊
一、什么是RNN
RNN与传统神经网络最大的区别在于,每次都会将前一次的输出结果,带到下一隐藏层中一起训练。如下图所示:
二、前期工作
1. 设置GPU
python
import tensorflow as tf
gpus = tf.config.list_physical_devices("GPU")
if gpus:
gpu0 = gpus[0] #如果有多个GPU,仅使用第0个GPU
tf.config.experimental.set_memory_growth(gpu0, True) #设置GPU显存用量按需使用
tf.config.set_visible_devices([gpu0],"GPU")
2. 导入数据
数据介绍:
age:年龄
sex:性别
cp:胸痛类型 (4 values)
trestbps:静息血压
chol:血清胆甾醇 (mg/dl)
fbs:空腹血糖 > 120 mg/dl
restecg:静息心电图结果 (值 0,1 ,2)
thalach:达到的最大心率
exang:运动诱发的心绞痛
oldpeak:相对于静止状态,运动引起的ST段压低
slope:运动峰值 ST 段的斜率
ca:荧光透视着色的主要血管数量 (0-3)
thal:0 = 正常;1 = 固定缺陷;2 = 可逆转的缺陷
target:0 = 心脏病发作的几率较小 1 = 心脏病发作的几率更大
python
import pandas as pd
import numpy as np
df = pd.read_csv(r"D:\Personal Data\Learning Data\DL Learning Data\heart.csv")
df
输出:
3. 检查数据
python
df.isnull().sum()
输出:
三、数据预处理
1. 划分数据集
python
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
x = df.iloc[:,:-1]
y = df.iloc[:,-1]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.1, random_state=1)
python
x_train.shape, y_train.shape
输出:
2. 标准化
python
# 将每一列特征标准化为标准正太分布,注意,标准化是针对每一列而言的
sc = StandardScaler()
x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)
x_train = x_train.reshape(x_train.shape[0], x_train.shape[1], 1)
x_test = x_test.reshape(x_test.shape[0], x_test.shape[1], 1)
3. 构建RNN模型
python
import tensorflow
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,LSTM,SimpleRNN
model = Sequential()
model.add(SimpleRNN(128, input_shape= (13,1),return_sequences=True,activation='relu'))
model.add(SimpleRNN(64,return_sequences=True, activation='relu'))
model.add(SimpleRNN(32, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.summary()
输出:
五、编译模型
python
opt = tf.keras.optimizers.Adam(learning_rate=1e-4)
model.compile(loss='binary_crossentropy', optimizer=opt,metrics=['accuracy'])
六、训练模型
python
epochs = 50
history = model.fit(x_train, y_train,
epochs=epochs,
batch_size=128,
validation_data=(x_test, y_test),
verbose=1)
部分输出:
python
model.evaluate(x_test,y_test)
输出:
七、模型评估
python
import matplotlib.pyplot as plt
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs_range = range(epochs)
plt.figure(figsize=(14, 4))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
最后准确率输出:
python
scores = model.evaluate(x_test, y_test, verbose=0)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
八、总结
- 注意numpy与panda以及matplotlib等之间的兼容性
- 注意对每一列的特征数据标准化处理