Python 我如何防止每次使用Keras开始新的培训课程时重新启动的丢失和准确性？
我正在学习如何通过在Keras中创建CNN来构建图像分类器。如何防止每次开始新的培训课程时重新开始课程。下面的代码包括一些我尝试过的注释掉的代码。谢谢 我曾尝试创建检查点，但准确性和损失似乎仍在重置。我还尝试了model.save（）和model.save_weights（），然后将它们加载到新模型中，但我的准确性和损失似乎仍然从一开始就存在Python 我如何防止每次使用Keras开始新的培训课程时重新启动的丢失和准确性？,python,keras,Python,Keras,我正在学习如何通过在Keras中创建CNN来构建图像分类器。如何防止每次开始新的培训课程时重新开始课程。下面的代码包括一些我尝试过的注释掉的代码。谢谢 我曾尝试创建检查点，但准确性和损失似乎仍在重置。我还尝试了model.save（）和model.save_weights（），然后将它们加载到新模型中，但我的准确性和损失似乎仍然从一开始就存在 导入 #导入CIFAR10数据 从keras.dataset导入cifar10 #进口keras utils 将keras.utils导入为utils #
导入
#导入CIFAR10数据
从keras.dataset导入cifar10
#进口keras utils
将keras.utils导入为utils
#导入序列模型
从keras.models导入顺序
#导入图层
从keras.layers导入致密、脱落、平坦
从keras.layers.Conv2D卷积导入，MaxPoolig2D
#规范化内核中的值
从keras.constraints导入maxnorm
#导入编译器优化器
从keras.optimizers导入新加坡元
#导入keras检查点
从keras.callbacks导入模型检查点
#进口h5py
进口h5py
最终进口
#加载cifar10数据
（x_列，y_列），（x_测试，y_测试）=cifar10.负载数据（）
#将序列和测试格式化为float32并除以255.0
x_train=x_train.astype（'float32'）/255.0
x_test=x_test.astype（'float32'）/255.0
#将y_列和y_测试更改为utils分类
y\u序列=utils.to\u范畴（y\u序列）
y_检验=utils.to_分类（y_检验）
#创建标签数组
标签=[“飞机”、“汽车”、“鸟”、“猫”、“鹿”、“狗”、“青蛙”、“马”、“船”、“卡车”]
顺序模型1
模型=顺序（）
add（Conv2D（filters=32，kernel\u size=（3,3），input\u shape=（32,32,3），activation='relu'，padding='same'，
核约束=最大范数（3）））
####添加第二个卷积层-MaxPoolig2D####
#将图像大小从32x32减小到16x16
#池大小：在输入的每个2x2部分中查找最大值
add（MaxPooling2D（池大小=（2,2）））
####展平特征####
#将矩阵转换为一维数组
model.add（展平（））
####添加第三个卷积层-第一个密集层，并注入其中####
#创建预测网络
#单位：第一层512个神经元
#激活：relu以确保准确性
#核约束：最大范数
添加（密集（单位=512，激活=relu，内核约束=maxnorm（3）））
####再加上第四个卷积-退出-杀死一些神经元-防止过度拟合-仅训练####
#提高可靠性
#速率：0.5意味着杀死一半的神经元
#仅在培训期间使用
模型添加（辍学率=0.5））
####添加第五个卷积层-第二个密集层-创建10个输出，因为我们有10个类别####
#为10个类别中的每一个生成输出
#单位：10个类别=10个输出单位
#激活='softmax'，因为我们正在计算10个类别（浮动）中每个类别的概率
添加（密集（单位=10，激活=softmax'））
##############################结束序列模型
##############################编译程序######################################
compile（optimizer=SGD（lr=0.01），loss='classifical\u crossentropy'，metrics=['accurity']）
################################终端编译器################################
################################保存数据###################################
#保存培训数据
model.save（filepath='model.h5'）
#基于最佳精度创建模型检查点
#文件路径='model.h5'
#checkpoint=ModelCheckpoint（filepath，monitor='val\u accurity'，save\u best\u only='True'，
#保存权重（仅保存为假，模式为最大，周期为1）
#回调\u列表=[检查点]
#节省重量
model.save_weights（'model_weights.h5'））
###############################结束保存数据################################
model.fit（x=x\u序列，y=y\u序列，验证\u分割=0.1，历代=20，批量大小=32，shuffle='True'）
from keras.datasets import cifar10
# import keras utils
import keras.utils as utils
# import Sequential model
from keras.models import Sequential
# import layers
from keras.layers import Dense, Dropout, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
# normalizes values in kernal
from keras.constraints import maxnorm
# import compiler optimizers
from keras.optimizers import SGD
# import keras checkpoint
from keras.callbacks import ModelCheckpoint
# import h5py
import h5py
# load cifar10 data
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
# format trains and tests to float32 and divide by 255.0
x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0
# change y_train and y_test to utils categorical
y_train = utils.to_categorical(y_train)
y_test = utils.to_categorical(y_test)
# create labels array
labels = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), input_shape=(32, 32, 3), activation='relu', padding='same',
kernel_constraint=maxnorm(3)))
#### add second convolution layer - MaxPooling2d ####
# decreases image size from 32x32 to 16x16
# pool_size: finds max value in each 2x2 section of input
model.add(MaxPooling2D(pool_size=(2, 2)))
#### flatten features ####
# converts matrix to a 1 dimensional array
model.add(Flatten())
#### add third convolution layer - first Dense and feed into it ####
# creates prediction network
# units: 512 neurons for first layer
# activation: relu for accuracy
# kernal_constraint: maxnorm
model.add(Dense(units=512, activation='relu', kernel_constraint=maxnorm(3)))
#### add fourth convolution later - Dropout - kills some neurons - prevents overfitting - TRAINING ONLY ####
# improves reliability
# rate: 0.5 means kill half the neurons
# only to be used while training
model.add(Dropout(rate=0.5))
#### add fifth convolution layer - Second Dense layer - Creates 10 outputs because we have 10 categories ####
# produces output for each of the 10 categories
# units: 10 categories = 10 output units
# activation = 'softmax' because we are calculating the probabilities of each of the 10 categories (floats)
model.add(Dense(units=10, activation='softmax'))
############################## END SEQUENTIAL MODEL ##########################
############################## COMPILER ######################################
model.compile(optimizer=SGD(lr=0.01), loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x=x_train, y=y_train, validation_split=0.1, epochs=20, batch_size=32, shuffle='True')
################################ END COMPILER ################################
################################ SAVE DATA ###################################
# saves the training data
model.save(filepath='model.h5')
# create model checkpoint based on best accuracy
#filepath = 'model.h5'
#checkpoint = ModelCheckpoint(filepath, monitor='val_accuracy', save_best_only='True',
#save_weights_only='False', mode='max', period=1)
#callbacks_list = [checkpoint]
# save weights
model.save_weights('model_weights.h5')
############################### END SAVE DATA ################################
让我知道这是否有效在您的案例中，问题是您在培训模型之前要保存模型。必须首先拟合进行训练的模型，然后保存模型。还随更改附加代码
from keras.datasets import cifar10
# import keras utils
import keras.utils as utils
# import Sequential model
from keras.models import Sequential
# import layers
from keras.layers import Dense, Dropout, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
# normalizes values in kernal
from keras.constraints import maxnorm
# import compiler optimizers
from keras.optimizers import SGD
# import keras checkpoint
from keras.callbacks import ModelCheckpoint
# import h5py
import h5py
# load cifar10 data
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
# format trains and tests to float32 and divide by 255.0
x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0
# change y_train and y_test to utils categorical
y_train = utils.to_categorical(y_train)
y_test = utils.to_categorical(y_test)
# create labels array
labels = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), input_shape=(32, 32, 3), activation='relu', padding='same',
kernel_constraint=maxnorm(3)))
#### add second convolution layer - MaxPooling2d ####
# decreases image size from 32x32 to 16x16
# pool_size: finds max value in each 2x2 section of input
model.add(MaxPooling2D(pool_size=(2, 2)))
#### flatten features ####
# converts matrix to a 1 dimensional array
model.add(Flatten())
#### add third convolution layer - first Dense and feed into it ####
# creates prediction network
# units: 512 neurons for first layer
# activation: relu for accuracy
# kernal_constraint: maxnorm
model.add(Dense(units=512, activation='relu', kernel_constraint=maxnorm(3)))
#### add fourth convolution later - Dropout - kills some neurons - prevents overfitting - TRAINING ONLY ####
# improves reliability
# rate: 0.5 means kill half the neurons
# only to be used while training
model.add(Dropout(rate=0.5))
#### add fifth convolution layer - Second Dense layer - Creates 10 outputs because we have 10 categories ####
# produces output for each of the 10 categories
# units: 10 categories = 10 output units
# activation = 'softmax' because we are calculating the probabilities of each of the 10 categories (floats)
model.add(Dense(units=10, activation='softmax'))
############################## END SEQUENTIAL MODEL ##########################
############################## COMPILER ######################################
model.compile(optimizer=SGD(lr=0.01), loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x=x_train, y=y_train, validation_split=0.1, epochs=20, batch_size=32, shuffle='True')
################################ END COMPILER ################################
################################ SAVE DATA ###################################
# saves the training data
model.save(filepath='model.h5')
# create model checkpoint based on best accuracy
#filepath = 'model.h5'
#checkpoint = ModelCheckpoint(filepath, monitor='val_accuracy', save_best_only='True',
#save_weights_only='False', mode='max', period=1)
#callbacks_list = [checkpoint]
# save weights
model.save_weights('model_weights.h5')
############################### END SAVE DATA ################################
让我知道这是否有效您应该在训练后保存模型，并使用
keras.models.load\u model# import CIFAR10 data
from keras.datasets import cifar10
# import keras utils
import keras.utils as utils
# import Sequential model
from keras.models import Sequential
# import layers
from keras.layers import Dense, Dropout, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
# normalizes values in kernal
from keras.constraints import maxnorm
# import compiler optimizers
from keras.optimizers import SGD
# import keras checkpoint
from keras.callbacks import ModelCheckpoint
# import h5py
import h5py
from keras.models import load_model
# load cifar10 data
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
# format trains and tests to float32 and divide by 255.0
x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0
# change y_train and y_test to utils categorical
y_train = utils.to_categorical(y_train)
y_test = utils.to_categorical(y_test)
# create labels array
labels = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), input_shape=(32, 32, 3), activation='relu', padding='same',
kernel_constraint=maxnorm(3)))
#### add second convolution layer - MaxPooling2d ####
# decreases image size from 32x32 to 16x16
# pool_size: finds max value in each 2x2 section of input
model.add(MaxPooling2D(pool_size=(2, 2)))
#### flatten features ####
# converts matrix to a 1 dimensional array
model.add(Flatten())
#### add third convolution layer - first Dense and feed into it ####
# creates prediction network
# units: 512 neurons for first layer
# activation: relu for accuracy
# kernal_constraint: maxnorm
model.add(Dense(units=512, activation='relu', kernel_constraint=maxnorm(3)))
#### add fourth convolution later - Dropout - kills some neurons - prevents overfitting - TRAINING ONLY ####
# improves reliability
# rate: 0.5 means kill half the neurons
# only to be used while training
model.add(Dropout(rate=0.5))
#### add fifth convolution layer - Second Dense layer - Creates 10 outputs because we have 10 categories ####
# produces output for each of the 10 categories
# units: 10 categories = 10 output units
# activation = 'softmax' because we are calculating the probabilities of each of the 10 categories (floats)
model.add(Dense(units=10, activation='softmax'))
############################## END SEQUENTIAL MODEL ##########################
############################## COMPILER ######################################
model.compile(optimizer=SGD(lr=0.01), loss='categorical_crossentropy', metrics=['accuracy'])
################################ END COMPILER ################################
################################ SAVE DATA ###################################
model = load_model('model.h5')
# create model checkpoint based on best accuracy
#filepath = 'model.h5'
#checkpoint = ModelCheckpoint(filepath, monitor='val_accuracy', save_best_only='True',
#save_weights_only='False', mode='max', period=1)
#callbacks_list = [checkpoint]
# # save weights
# model.save_weights('model_weights.h5')
############################### END SAVE DATA ################################
model.fit(x=x_train, y=y_train, validation_split=0.1, epochs=1, batch_size=32, shuffle='True')
# saves the training data
model.save(filepath='model.h5')