Python实战之MNIST手写数字识别详解

目录

• 数据集介绍
• 1.数据预处理
• 2.网络搭建
• 3.网络配置
• 关于优化器
• 关于损失函数
• 关于指标
• 4.网络训练与测试
• 5.绘制loss和accuracy随着epochs的变化图
• 6.完整代码

def load_data(path='mnist.npz'):
  """Loads the [MNIST dataset](http://yann.lecun.com/exdb/mnist/).
  This is a dataset of 60,000 28x28 grayscale images of the 10 digits,
  along with a test set of 10,000 images.
  More info can be found at the
  [MNIST homepage](http://yann.lecun.com/exdb/mnist/).
  Arguments:
      path: path where to cache the dataset locally
          (relative to `~/.keras/datasets`).
  Returns:
      Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
      **x_train, x_test**: uint8 arrays of grayscale image data with shapes
        (num_samples, 28, 28).
      **y_train, y_test**: uint8 arrays of digit labels (integers in range 0-9)
        with shapes (num_samples,).
  """

[0,1,9]-------->[ [1,0,0,0,0,0,0,0,0,0],
                  [0,1,0,0,0,0,0,0,0,0],
                  [0,0,0,0,0,0,0,0,0,1] ]        

def one_hot(sequences,col):
        resuts=np.zeros((len(sequences),col))
        # for i,sequence in enumerate(sequences):
        #         resuts[i,sequence]=1
        for i in range(len(sequences)):
                for j in range(len(sequences[i])):
                        resuts[i,sequences[i][j]]=1
        return resuts

def data_preprocess():
    (train_images, train_labels), (test_images, test_labels) = mnist.load_data()
    train_images = train_images.reshape((60000, 28, 28, 1))
    train_images = train_images.astype('float32') / 255
    #print(train_images[0])
    test_images = test_images.reshape((10000, 28, 28, 1))
    test_images = test_images.astype('float32') / 255
    train_labels = to_categorical(train_labels)
    test_labels = to_categorical(test_labels)
    return train_images,train_labels,test_images,test_labels

def build_module():
    model = models.Sequential()
    #第一层卷积层，首层需要指出input_shape形状
    model.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)))
    #第二层最大池化层
    model.add(layers.MaxPooling2D((2,2)))
    #第三层卷积层
    model.add(layers.Conv2D(64, (3,3), activation='relu'))
    #第四层最大池化层
    model.add(layers.MaxPooling2D((2,2)))
    #第五层卷积层
    model.add(layers.Conv2D(64, (3,3), activation='relu'))
    #第六层Flatten层，将3D张量平铺为向量
    model.add(layers.Flatten())
    #第七层全连接层
    model.add(layers.Dense(64, activation='relu'))
    #第八层softmax层，进行分类
    model.add(layers.Dense(10, activation='softmax'))
    return model

  def compile(self,
              optimizer='rmsprop',
              loss=None,
              metrics=None,
              loss_weights=None,
              weighted_metrics=None,
              run_eagerly=None,
              steps_per_execution=None,
              **kwargs):
    """Configures the model for training.

keras.optimizers.RMSprop(lr=0.001, rho=0.9, epsilon=None, decay=0.0)
model.compile(optimizer='rmsprop'，loss='mean_squared_error')

lr: float >= 0. 学习率。
rho: float >= 0. RMSProp梯度平方的移动均值的衰减率.
epsilon: float >= 0. 模糊因子. 若为 None, 默认为 K.epsilon()。
decay: float >= 0. 每次参数更新后学习率衰减值。

import keras.backend as K
def mean_pred(y_true, y_pred):
    return K.mean(y_pred)
model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy', mean_pred])

def fit(self,
          x=None,
          y=None,
          batch_size=None,
          epochs=1,
          verbose=1,
          callbacks=None,
          validation_split=0.,
          validation_data=None,
          shuffle=True,
          class_weight=None,
          sample_weight=None,
          initial_epoch=0,
          steps_per_epoch=None,
          validation_steps=None,
          validation_batch_size=None,
          validation_freq=1,
          max_queue_size=10,
          workers=1,
          use_multiprocessing=False):

model.fit(train_images, train_labels, epochs = 5, batch_size=64)

test_loss, test_acc = model.evaluate(test_images, test_labels)

Returns:
        Scalar test loss (if the model has a single output and no metrics)
        or list of scalars (if the model has multiple outputs
        and/or metrics). The attribute `model.metrics_names` will give you
        the display labels for the scalar outputs.

Returns:
        A `History` object. Its `History.history` attribute is
        a record of training loss values and metrics values
        at successive epochs, as well as validation loss values
        and validation metrics values (if applicable).

def draw_loss(history):
    loss=history.history['loss']
    epochs=range(1,len(loss)+1)
    plt.subplot(1,2,1)#第一张图
    plt.plot(epochs,loss,'bo',label='Training loss')
    plt.title("Training loss")
    plt.xlabel('Epochs')
    plt.ylabel('Loss')
    plt.legend()
    plt.subplot(1,2,2)#第二张图
    accuracy=history.history['accuracy']
    plt.plot(epochs,accuracy,'bo',label='Training accuracy')
    plt.title("Training accuracy")
    plt.xlabel('Epochs')
    plt.ylabel('Accuracy')
    plt.suptitle("Train data")
    plt.legend()
    plt.show()

from tensorflow.keras.datasets import mnist
from tensorflow.keras import models
from tensorflow.keras import layers
from tensorflow.keras.utils import to_categorical
import matplotlib.pyplot as plt
import numpy as np
def data_preprocess():
    (train_images, train_labels), (test_images, test_labels) = mnist.load_data()
    train_images = train_images.reshape((60000, 28, 28, 1))
    train_images = train_images.astype('float32') / 255
    #print(train_images[0])
    test_images = test_images.reshape((10000, 28, 28, 1))
    test_images = test_images.astype('float32') / 255
    train_labels = to_categorical(train_labels)
    test_labels = to_categorical(test_labels)
    return train_images,train_labels,test_images,test_labels
#搭建网络
def build_module():
    model = models.Sequential()
    #第一层卷积层
    model.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)))
    #第二层最大池化层
    model.add(layers.MaxPooling2D((2,2)))
    #第三层卷积层
    model.add(layers.Conv2D(64, (3,3), activation='relu'))
    #第四层最大池化层
    model.add(layers.MaxPooling2D((2,2)))
    #第五层卷积层
    model.add(layers.Conv2D(64, (3,3), activation='relu'))
    #第六层Flatten层，将3D张量平铺为向量
    model.add(layers.Flatten())
    #第七层全连接层
    model.add(layers.Dense(64, activation='relu'))
    #第八层softmax层，进行分类
    model.add(layers.Dense(10, activation='softmax'))
    return model
def draw_loss(history):
    loss=history.history['loss']
    epochs=range(1,len(loss)+1)
    plt.subplot(1,2,1)#第一张图
    plt.plot(epochs,loss,'bo',label='Training loss')
    plt.title("Training loss")
    plt.xlabel('Epochs')
    plt.ylabel('Loss')
    plt.legend()
    plt.subplot(1,2,2)#第二张图
    accuracy=history.history['accuracy']
    plt.plot(epochs,accuracy,'bo',label='Training accuracy')
    plt.title("Training accuracy")
    plt.xlabel('Epochs')
    plt.ylabel('Accuracy')
    plt.suptitle("Train data")
    plt.legend()
    plt.show()
if __name__=='__main__':
    train_images,train_labels,test_images,test_labels=data_preprocess()
    model=build_module()
    print(model.summary())
    model.compile(optimizer='rmsprop', loss = 'categorical_crossentropy', metrics=['accuracy'])
    history=model.fit(train_images, train_labels, epochs = 5, batch_size=64)
    draw_loss(history)
    test_loss, test_acc = model.evaluate(test_images, test_labels)
    print('test_loss=',test_loss,'  test_acc = ', test_acc)