keras搭建CNN所用函数-以MNIST数据集为例

最新推荐文章于 2022-05-15 11:21:16 发布

Weyoung_

最新推荐文章于 2022-05-15 11:21:16 发布

阅读量713

点赞数

分类专栏： keras

本文链接：https://blog.csdn.net/Weyoung_/article/details/79857268

版权

keras 专栏收录该内容

2 篇文章 0 订阅

订阅专栏

源代码链接：https://www.kaggle.com/yassineghouzam/introduction-to-cnn-keras-0-997-top-6

sns.countplot(label):作图，统计label中每个不同的label出现的次数

DataFrame.values.reshape(shape):以shape重新规划DataFrame中的值，eg:shape=(-1,28,28,1)，-1表示此维度不限数目

注意：转换后DataFrame类型变为ndarray类型

keras.utils.np_utils.to_categorical(Y_train, num_classes = n):将标量表示的Y_train变为one hot向量，list变为矩阵

g = plt.imshow(X_train[0][:,:,0],cmap='gray'),若不加cmap='gray',灰度原图作出的图可能是彩色的,或在前加入plt.gray() 命令

keras定义神经网络：

# Set the CNN model 
# my CNN architechture is In -> [[Conv2D->relu]*2 -> MaxPool2D -> Dropout]*2 -> Flatten -> Dense -> Dropout -> Out

from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D

model = Sequential()

model.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', 
                 activation ='relu', input_shape = (28,28,1)))
model.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'Same', 
                 activation ='relu'))
model.add(MaxPool2D(pool_size=(2,2)))
model.add(Dropout(0.25))

数据增强：增加原始数据的variaions，例如数字不在图像中心，数字大小不同

常用方法：grayscales, horizontal flips, vertical flips, random crops, color jitters, translations, rotations, and much more.

# With data augmentation to prevent overfitting (accuracy 0.99286)

datagen = ImageDataGenerator(
        featurewise_center=False,  # set input mean to 0 over the dataset
        samplewise_center=False,  # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)
        zoom_range = 0.1, # Randomly zoom image 
        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=False,  # randomly flip images
        vertical_flip=False)  # randomly flip images


datagen.fit(X_train)

应用数据增强和模拟退火算法后，keras的fit函数形式改变：

# Fit the model
history = model.fit_generator(datagen.flow(X_train,Y_train, batch_size=batch_size),
                              epochs = epochs, validation_data = (X_val,Y_val),
                              verbose = 2, steps_per_epoch=X_train.shape[0] // batch_size
                              , callbacks=[learning_rate_reduction])

根据训练结果作图：

# Plot the loss and accuracy curves for training and validation 
fig, ax = plt.subplots(2,1)
ax[0].plot(history.history['loss'], color='b', label="Training loss")
ax[0].plot(history.history['val_loss'], color='r', label="validation loss",axes =ax[0])
legend = ax[0].legend(loc='best', shadow=True)

ax[1].plot(history.history['acc'], color='b', label="Training accuracy")
ax[1].plot(history.history['val_acc'], color='r',label="Validation accuracy")
legend = ax[1].legend(loc='best', shadow=True)