使用Keras建立模型并训练等一系列操作方式
更新时间：2020年07月02日 12:03:24 作者：夏洛的网
这篇文章主要介绍了使用Keras建立模型并训练等一系列操作方式，具有很好的参考价值，希望对大家有所帮助。一起跟随小编过来看看吧
由于Keras是一种建立在已有深度学习框架上的二次框架，其使用起来非常方便，其后端实现有两种方法，theano和tensorflow。由于自己平时用tensorflow，所以选择后端用tensorflow的Keras，代码写起来更加方便。
1、建立模型
Keras分为两种不同的建模方式，
Sequential models：这种方法用于实现一些简单的模型。你只需要向一些存在的模型中添加层就行了。
Functional API：Keras的API是非常强大的，你可以利用这些API来构造更加复杂的模型，比如多输出模型，有向无环图等等。
这里采用sequential models方法。
构建序列模型。
def define_model():
model = Sequential()
# setup first conv layer
model.add(Conv2D(32, (3, 3), activation="relu",
input_shape=(120, 120, 3), padding='same')) # [10, 120, 120, 32]
# setup first maxpooling layer
model.add(MaxPooling2D(pool_size=(2, 2))) # [10, 60, 60, 32]
# setup second conv layer
model.add(Conv2D(8, kernel_size=(3, 3), activation="relu",
padding='same')) # [10, 60, 60, 8]
# setup second maxpooling layer
model.add(MaxPooling2D(pool_size=(3, 3))) # [10, 20, 20, 8]
# add bianping layer, 3200 = 20 * 20 * 8
model.add(Flatten()) # [10, 3200]
# add first full connection layer
model.add(Dense(512, activation='sigmoid')) # [10, 512]
# add dropout layer
model.add(Dropout(0.5))
# add second full connection layer
model.add(Dense(4, activation='softmax')) # [10, 4]
return model
可以看到定义模型时输出的网络结构。
2、准备数据
def load_data(resultpath):
datapath = os.path.join(resultpath, "data10_4.npz")
if os.path.exists(datapath):
data = np.load(datapath)
X, Y = data["X"], data["Y"]
else:
X = np.array(np.arange(432000)).reshape(10, 120, 120, 3)
Y = [0, 0, 1, 1, 2, 2, 3, 3, 2, 0]
X = X.astype('float32')
Y = np_utils.to_categorical(Y, 4)
np.savez(datapath, X=X, Y=Y)
print('Saved dataset to dataset.npz.')
print('X_shape:{}\nY_shape:{}'.format(X.shape, Y.shape))
return X, Y
3、训练模型
def train_model(resultpath):
model = define_model()
# if want to use SGD, first define sgd, then set optimizer=sgd
sgd = SGD(lr=0.001, decay=1e-6, momentum=0, nesterov=True)
# select loss\optimizer\
model.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
model.summary()
# draw the model structure
plot_model(model, show_shapes=True,
to_file=os.path.join(resultpath, 'model.png'))
# load data
X, Y = load_data(resultpath)
# split train and test data
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, test_size=0.2, random_state=2)
# input data to model and train
history = model.fit(X_train, Y_train, batch_size=2, epochs=10,
validation_data=(X_test, Y_test), verbose=1, shuffle=True)
# evaluate the model
loss, acc = model.evaluate(X_test, Y_test, verbose=0)
print('Test loss:', loss)
print('Test accuracy:', acc)
可以看到训练时输出的日志。因为是随机数据，没有意义，这里训练的结果不必计较，只是练习而已。
保存下来的模型结构：
4、保存与加载模型并测试
有两种保存方式
4.1 直接保存模型h5
保存：
def my_save_model(resultpath): model = train_model(resultpath) # the first way to save model model.save(os.path.join(resultpath, 'my_model.h5'))
加载：
def my_load_model(resultpath):
# test data
X = np.array(np.arange(86400)).reshape(2, 120, 120, 3)
Y = [0, 1]
X = X.astype('float32')
Y = np_utils.to_categorical(Y, 4)
# the first way of load model
model2 = load_model(os.path.join(resultpath, 'my_model.h5'))
model2.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
test_loss, test_acc = model2.evaluate(X, Y, verbose=0)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
y = model2.predict_classes(X)
print("predicct is: ", y)
4.2 分别保存网络结构和权重
保存：
def my_save_model(resultpath): model = train_model(resultpath) # the secon way : save trained network structure and weights model_json = model.to_json() open(os.path.join(resultpath, 'my_model_structure.json'), 'w').write(model_json) model.save_weights(os.path.join(resultpath, 'my_model_weights.hd5'))
加载：
def my_load_model(resultpath):
# test data
X = np.array(np.arange(86400)).reshape(2, 120, 120, 3)
Y = [0, 1]
X = X.astype('float32')
Y = np_utils.to_categorical(Y, 4)
# the second way : load model structure and weights
model = model_from_json(open(os.path.join(resultpath, 'my_model_structure.json')).read())
model.load_weights(os.path.join(resultpath, 'my_model_weights.hd5'))
model.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
test_loss, test_acc = model.evaluate(X, Y, verbose=0)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
y = model.predict_classes(X)
print("predicct is: ", y)
可以看到，两次的结果是一样的。
5、完整代码
from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Dropout
from keras.losses import categorical_crossentropy
from keras.optimizers import Adam
from keras.utils.vis_utils import plot_model
from keras.optimizers import SGD
from keras.models import model_from_json
from keras.models import load_model
from keras.utils import np_utils
import numpy as np
import os
from sklearn.model_selection import train_test_split
def load_data(resultpath):
datapath = os.path.join(resultpath, "data10_4.npz")
if os.path.exists(datapath):
data = np.load(datapath)
X, Y = data["X"], data["Y"]
else:
X = np.array(np.arange(432000)).reshape(10, 120, 120, 3)
Y = [0, 0, 1, 1, 2, 2, 3, 3, 2, 0]
X = X.astype('float32')
Y = np_utils.to_categorical(Y, 4)
np.savez(datapath, X=X, Y=Y)
print('Saved dataset to dataset.npz.')
print('X_shape:{}\nY_shape:{}'.format(X.shape, Y.shape))
return X, Y
def define_model():
model = Sequential()
# setup first conv layer
model.add(Conv2D(32, (3, 3), activation="relu",
input_shape=(120, 120, 3), padding='same')) # [10, 120, 120, 32]
# setup first maxpooling layer
model.add(MaxPooling2D(pool_size=(2, 2))) # [10, 60, 60, 32]
# setup second conv layer
model.add(Conv2D(8, kernel_size=(3, 3), activation="relu",
padding='same')) # [10, 60, 60, 8]
# setup second maxpooling layer
model.add(MaxPooling2D(pool_size=(3, 3))) # [10, 20, 20, 8]
# add bianping layer, 3200 = 20 * 20 * 8
model.add(Flatten()) # [10, 3200]
# add first full connection layer
model.add(Dense(512, activation='sigmoid')) # [10, 512]
# add dropout layer
model.add(Dropout(0.5))
# add second full connection layer
model.add(Dense(4, activation='softmax')) # [10, 4]
return model
def train_model(resultpath):
model = define_model()
# if want to use SGD, first define sgd, then set optimizer=sgd
sgd = SGD(lr=0.001, decay=1e-6, momentum=0, nesterov=True)
# select loss\optimizer\
model.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
model.summary()
# draw the model structure
plot_model(model, show_shapes=True,
to_file=os.path.join(resultpath, 'model.png'))
# load data
X, Y = load_data(resultpath)
# split train and test data
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, test_size=0.2, random_state=2)
# input data to model and train
history = model.fit(X_train, Y_train, batch_size=2, epochs=10,
validation_data=(X_test, Y_test), verbose=1, shuffle=True)
# evaluate the model
loss, acc = model.evaluate(X_test, Y_test, verbose=0)
print('Test loss:', loss)
print('Test accuracy:', acc)
return model
def my_save_model(resultpath):
model = train_model(resultpath)
# the first way to save model
model.save(os.path.join(resultpath, 'my_model.h5'))
# the secon way : save trained network structure and weights
model_json = model.to_json()
open(os.path.join(resultpath, 'my_model_structure.json'), 'w').write(model_json)
model.save_weights(os.path.join(resultpath, 'my_model_weights.hd5'))
def my_load_model(resultpath):
# test data
X = np.array(np.arange(86400)).reshape(2, 120, 120, 3)
Y = [0, 1]
X = X.astype('float32')
Y = np_utils.to_categorical(Y, 4)
# the first way of load model
model2 = load_model(os.path.join(resultpath, 'my_model.h5'))
model2.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
test_loss, test_acc = model2.evaluate(X, Y, verbose=0)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
y = model2.predict_classes(X)
print("predicct is: ", y)
# the second way : load model structure and weights
model = model_from_json(open(os.path.join(resultpath, 'my_model_structure.json')).read())
model.load_weights(os.path.join(resultpath, 'my_model_weights.hd5'))
model.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
test_loss, test_acc = model.evaluate(X, Y, verbose=0)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
y = model.predict_classes(X)
print("predicct is: ", y)
def main():
resultpath = "result"
#train_model(resultpath)
#my_save_model(resultpath)
my_load_model(resultpath)
if __name__ == "__main__":
main()
以上这篇使用Keras建立模型并训练等一系列操作方式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脚本之家。
相关文章
这篇文章主要为大家详细介绍了python绘制圆柱体的方法，具有一定的参考价值，感兴趣的小伙伴们可以参考一下2018-07-07
SciPy是一个强大的Python库，提供了丰富的科学计算和数据分析工具，本文我们将探讨如何使用Python和SciPy库进行统计分析和建模，感兴趣的可以学习一下2023-06-06
在数据分析和处理中,Pandas是一个非常强大的工具,它提供了灵活的数据结构和丰富的操作方法,使得数据处理变得更加简单高效,其中,对数据的列名和索引进行重命名是常见的需求之一,本文将从基础概念出发,逐步深入探讨如何使用Pandas对列名和索引进行重命名2024-12-12
int() 函数用于将一个字符串会数字转换为整型。接下来通过本文给大家介绍python 中的int()函数的相关知识，感兴趣的朋友一起看看吧2017-10-10
这篇文章主要介绍了Python 3.x对.CSV数据按任意行、列读取的过程，具有很好的参考价值，希望对大家有所帮助。2022-05-05
这篇文章主要介绍了matlab中二维插值函数interp2的使用详解，具有很好的参考价值，希望对大家有所帮助。一起跟随小编过来看看吧2020-04-04
本篇文章主要介绍了Python内置函数的使用方法，小编觉得挺不错的，现在分享给大家，也给大家做个参考。一起跟随小编过来看看吧2021-10-10
这篇文章主要为大家分享了一个Python实战小案例——生成有关联单选问卷，并且能根据问卷总分数生成对应判断文案结果，感兴趣的可以了解一下2023-04-04
相信大家对进度条一定不陌生了，很多安装或者下载都会出现进度条，本文主要介绍了Python实现实时显示进度条的6种方法，具有一定的参考价值，感兴趣的可以了解一下2021-12-12
本文主要介绍了pandas loc与iloc用法及区别，文中通过示例代码介绍的非常详细，对大家的学习或者工作具有一定的参考学习价值，需要的朋友们下面随着小编来一起学习学习吧2023-05-05
最新评论