keras绘制acc和loss曲线图实例


Posted in Python onJune 15, 2020

我就废话不多说了,大家还是直接看代码吧!

#加载keras模块
from __future__ import print_function
import numpy as np
np.random.seed(1337) # for reproducibility

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation
from keras.optimizers import SGD, Adam, RMSprop
from keras.utils import np_utils
import matplotlib.pyplot as plt
%matplotlib inline

#写一个LossHistory类,保存loss和acc
class LossHistory(keras.callbacks.Callback):
 def on_train_begin(self, logs={}):
  self.losses = {'batch':[], 'epoch':[]}
  self.accuracy = {'batch':[], 'epoch':[]}
  self.val_loss = {'batch':[], 'epoch':[]}
  self.val_acc = {'batch':[], 'epoch':[]}

 def on_batch_end(self, batch, logs={}):
  self.losses['batch'].append(logs.get('loss'))
  self.accuracy['batch'].append(logs.get('acc'))
  self.val_loss['batch'].append(logs.get('val_loss'))
  self.val_acc['batch'].append(logs.get('val_acc'))

 def on_epoch_end(self, batch, logs={}):
  self.losses['epoch'].append(logs.get('loss'))
  self.accuracy['epoch'].append(logs.get('acc'))
  self.val_loss['epoch'].append(logs.get('val_loss'))
  self.val_acc['epoch'].append(logs.get('val_acc'))

 def loss_plot(self, loss_type):
  iters = range(len(self.losses[loss_type]))
  plt.figure()
  # acc
  plt.plot(iters, self.accuracy[loss_type], 'r', label='train acc')
  # loss
  plt.plot(iters, self.losses[loss_type], 'g', label='train loss')
  if loss_type == 'epoch':
   # val_acc
   plt.plot(iters, self.val_acc[loss_type], 'b', label='val acc')
   # val_loss
   plt.plot(iters, self.val_loss[loss_type], 'k', label='val loss')
  plt.grid(True)
  plt.xlabel(loss_type)
  plt.ylabel('acc-loss')
  plt.legend(loc="upper right")
  plt.show()
#变量初始化
batch_size = 128 
nb_classes = 10
nb_epoch = 20

# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

#建立模型 使用Sequential()
model = Sequential()
model.add(Dense(512, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax'))

#打印模型
model.summary()

#训练与评估
#编译模型
model.compile(loss='categorical_crossentropy',
    optimizer=RMSprop(),
    metrics=['accuracy'])
#创建一个实例history
history = LossHistory()

#迭代训练(注意这个地方要加入callbacks)
model.fit(X_train, Y_train,
   batch_size=batch_size, nb_epoch=nb_epoch,
   verbose=1, 
   validation_data=(X_test, Y_test),
   callbacks=[history])

#模型评估
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])

#绘制acc-loss曲线
history.loss_plot('epoch')

keras绘制acc和loss曲线图实例

补充知识:keras中自定义验证集的性能评估(ROC,AUC)

在keras中自带的性能评估有准确性以及loss,当需要以auc作为评价验证集的好坏时,就得自己写个评价函数了:

from sklearn.metrics import roc_auc_score
from keras import backend as K

# AUC for a binary classifier
def auc(y_true, y_pred):
 ptas = tf.stack([binary_PTA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0)
 pfas = tf.stack([binary_PFA(y_true,y_pred,k) for k in np.linspace(0, 1, 1000)],axis=0)
 pfas = tf.concat([tf.ones((1,)) ,pfas],axis=0)
 binSizes = -(pfas[1:]-pfas[:-1])
 s = ptas*binSizes
 return K.sum(s, axis=0)
#------------------------------------------------------------------------------------
# PFA, prob false alert for binary classifier
def binary_PFA(y_true, y_pred, threshold=K.variable(value=0.5)):
 y_pred = K.cast(y_pred >= threshold, 'float32')
 # N = total number of negative labels
 N = K.sum(1 - y_true)
 # FP = total number of false alerts, alerts from the negative class labels
 FP = K.sum(y_pred - y_pred * y_true)
 return FP/N
#-----------------------------------------------------------------------------------
# P_TA prob true alerts for binary classifier
def binary_PTA(y_true, y_pred, threshold=K.variable(value=0.5)):
 y_pred = K.cast(y_pred >= threshold, 'float32')
 # P = total number of positive labels
 P = K.sum(y_true)
 # TP = total number of correct alerts, alerts from the positive class labels
 TP = K.sum(y_pred * y_true)
 return TP/P
 
#接着在模型的compile中设置metrics
#如下例子,我用的是RNN做分类
from keras.models import Sequential
from keras.layers import Dense, Dropout
import keras
from keras.layers import GRU

model = Sequential()
model.add(keras.layers.core.Masking(mask_value=0., input_shape=(max_lenth, max_features))) #masking用于变长序列输入
model.add(GRU(units=n_hidden_units,activation='selu',kernel_initializer='orthogonal', recurrent_initializer='orthogonal',
    bias_initializer='zeros', kernel_regularizer=regularizers.l2(0.01), recurrent_regularizer=regularizers.l2(0.01),
    bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, recurrent_constraint=None,
    bias_constraint=None, dropout=0.5, recurrent_dropout=0.0, implementation=1, return_sequences=False,
    return_state=False, go_backwards=False, stateful=False, unroll=False)) 
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy',
    optimizer='adam',
    metrics=[auc]) #写入自定义评价函数

接下来就自己作预测了...

方法二:

from sklearn.metrics import roc_auc_score
import keras
class RocAucMetricCallback(keras.callbacks.Callback):
 def __init__(self, predict_batch_size=1024, include_on_batch=False):
  super(RocAucMetricCallback, self).__init__()
  self.predict_batch_size=predict_batch_size
  self.include_on_batch=include_on_batch
 
 def on_batch_begin(self, batch, logs={}):
  pass
 
 def on_batch_end(self, batch, logs={}):
  if(self.include_on_batch):
   logs['roc_auc_val']=float('-inf')
   if(self.validation_data):
    logs['roc_auc_val']=roc_auc_score(self.validation_data[1], 
             self.model.predict(self.validation_data[0],
                  batch_size=self.predict_batch_size))
 def on_train_begin(self, logs={}):
  if not ('roc_auc_val' in self.params['metrics']):
   self.params['metrics'].append('roc_auc_val')
 
 def on_train_end(self, logs={}):
  pass
 
 def on_epoch_begin(self, epoch, logs={}):
  pass
 
 def on_epoch_end(self, epoch, logs={}):
  logs['roc_auc_val']=float('-inf')
  if(self.validation_data):
   logs['roc_auc_val']=roc_auc_score(self.validation_data[1], 
            self.model.predict(self.validation_data[0],
                 batch_size=self.predict_batch_size))
import numpy as np
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import GRU
import keras
from keras.callbacks import EarlyStopping
from sklearn.metrics import roc_auc_score
from keras import metrics
 
cb = [
 my_callbacks.RocAucMetricCallback(), # include it before EarlyStopping!
 EarlyStopping(monitor='roc_auc_val',patience=300, verbose=2,mode='max')
]
model = Sequential()
model.add(keras.layers.core.Masking(mask_value=0., input_shape=(max_lenth, max_features)))
# model.add(Embedding(input_dim=max_features+1, output_dim=64,mask_zero=True))
model.add(GRU(units=n_hidden_units,activation='selu',kernel_initializer='orthogonal', recurrent_initializer='orthogonal',
    bias_initializer='zeros', kernel_regularizer=regularizers.l2(0.01), recurrent_regularizer=regularizers.l2(0.01),
    bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, recurrent_constraint=None,
    bias_constraint=None, dropout=0.5, recurrent_dropout=0.0, implementation=1, return_sequences=False,
    return_state=False, go_backwards=False, stateful=False, unroll=False)) #input_shape=(max_lenth, max_features),
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
 
model.compile(loss='binary_crossentropy',
    optimizer='adam',
    metrics=[auc]) #这里就可以写其他评估标准
model.fit(x_train, y_train, batch_size=train_batch_size, epochs=training_iters, verbose=2,
   callbacks=cb,validation_split=0.2,
   shuffle=True, class_weight=None, sample_weight=None, initial_epoch=0)

亲测有效!

以上这篇keras绘制acc和loss曲线图实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持三水点靠木。

Python 相关文章推荐
Python with用法实例
Apr 14 Python
Python字符串切片操作知识详解
Mar 28 Python
python下调用pytesseract识别某网站验证码的实现方法
Jun 06 Python
Windows下anaconda安装第三方包的方法小结(tensorflow、gensim为例)
Apr 05 Python
利用Python求阴影部分的面积实例代码
Dec 05 Python
python中使用ctypes调用so传参设置遇到的问题及解决方法
Jun 19 Python
使用python的pandas为你的股票绘制趋势图
Jun 26 Python
pandas计算最大连续间隔的方法
Jul 04 Python
tensorflow之并行读入数据详解
Feb 05 Python
django自带的权限管理Permission用法说明
May 13 Python
Python基于pillow库实现生成图片水印
Sep 14 Python
pytest配置文件pytest.ini的详细使用
Apr 17 Python
Python定义一个函数的方法
Jun 15 #Python
python是怎么被发明的
Jun 15 #Python
Keras 利用sklearn的ROC-AUC建立评价函数详解
Jun 15 #Python
Python如何在windows环境安装pip及rarfile
Jun 15 #Python
keras训练曲线,混淆矩阵,CNN层输出可视化实例
Jun 15 #Python
Python3 requests模块如何模仿浏览器及代理
Jun 15 #Python
keras读取训练好的模型参数并把参数赋值给其它模型详解
Jun 15 #Python
You might like
网站用php实现paypal整合方法
2010/11/28 PHP
thinkPHP5框架中widget的功能与用法详解
2018/06/11 PHP
动态添加js事件实现代码
2009/03/12 Javascript
强大的jquery插件jqeuryUI做网页对话框效果!简单
2011/04/14 Javascript
Javascript对象中关于setTimeout和setInterval的this介绍
2012/07/21 Javascript
Jquery实现三层遍历删除功能代码
2013/04/23 Javascript
js获取和设置属性的方法
2014/02/20 Javascript
jQuery插件制作之参数用法实例分析
2015/06/01 Javascript
JavaScript编程中window的location与history对象详解
2015/10/26 Javascript
js多个物体运动功能实例分析
2016/12/20 Javascript
基于Vue单文件组件详解
2017/09/15 Javascript
详解Node使用Puppeteer完成一次复杂的爬虫
2018/04/18 Javascript
bootstrap模态框关闭后清除模态框的数据方法
2018/08/10 Javascript
JS与SQL方式随机生成高强度密码示例
2018/12/29 Javascript
vue基础之事件简写、事件对象、冒泡、默认行为、键盘事件实例分析
2019/03/11 Javascript
qrcode生成二维码微信长按无法识别问题的解决
2019/04/04 Javascript
微信小程序 授权登录详解(附完整源码)
2019/08/23 Javascript
JS forEach跳出循环2种实现方法
2020/06/24 Javascript
浅谈pyqt5中信号与槽的认识
2019/02/17 Python
python3利用Socket实现通信的方法示例
2019/05/06 Python
python opencv摄像头的简单应用
2019/06/06 Python
python 实现多线程下载m3u8格式视频并使用fmmpeg合并
2019/11/15 Python
python对文件的操作方法汇总
2020/02/28 Python
python同时遍历两个list用法说明
2020/05/02 Python
如何解决python多种版本冲突问题
2020/10/13 Python
基于Pytorch版yolov5的滑块验证码破解思路详解
2021/02/25 Python
伦敦高级内衣品牌:Agent Provocateur(大内密探)
2016/08/23 全球购物
手机配件第一品牌:ZAGG
2017/05/28 全球购物
请编程遍历页面上所有 TextBox 控件并给它赋值为 string.Empty
2015/12/03 面试题
保卫科工作岗位职责
2014/03/01 职场文书
党的群众路线教育实践活动个人承诺书
2014/05/22 职场文书
刑事辩护授权委托书格式
2014/10/13 职场文书
2014年人事部工作总结
2014/12/03 职场文书
医院保洁员岗位职责
2015/02/13 职场文书
vue+elementui 实现新增和修改共用一个弹框的完整代码
2021/06/08 Vue.js
Win11 vmware不兼容怎么办?Win11与VMware虚拟机不兼容的解决方法
2023/01/09 数码科技