python深度学习第二章笔记

2.1MNIST实例

# coding=utf-8
"""
__project_ = 'Python深度学习'
__file_name__ = '2.1MNIST'
__author__ = 'WIN10'
__time__ = '2020/4/11 11:22'
__product_name = PyCharm

"""
from keras.datasets import mnist
from keras import models
from keras import layers
from keras.utils import to_categorical
#读取数据
(train_images,train_labels),(test_images,test_labels)=mnist.load_data()

#数据处理
train_images=train_images.reshape(60000,28*28)
train_images=train_images.astype('float32')/255

test_images=test_images.reshape(10000,28*28)
test_images=test_images.astype('float32')/255

train_labels=to_categorical(train_labels)
test_labels=to_categorical(test_labels)

#构建网络，Dense 全连接层
network=models.Sequential()
network.add(layers.Dense(512,activation='relu',input_shape=(28*28,)))
network.add(layers.Dense(10,activation='softmax'))

#编译 需要3个参数 ，损失函数、优化器、训练和测试过程中的键控指标
network.compile(optimizer='rmsprop',
                loss='categorical_crossentropy',
                metrics=['accuracy'])

#训练
network.fit(train_images,train_labels,epochs=5,batch_size=128)
#测试
test_loss,test_acc=network.evaluate(test_images,test_labels)
print(test_loss,test_acc)

2.2张量的定义

# coding=utf-8
"""
__project_ = 'Python深度学习'
__file_name__ = '2.2张量'
__author__ = 'WIN10'
__time__ = '2020/4/11 11:39'
__product_name = PyCharm

"""
import numpy as np
from keras.datasets import mnist
import matplotlib.pyplot as plt
#一个数字的叫标量
x1=np.array(12)
#数字组成的数组叫向量
x2=np.array([12,3,6,14,7])
#向量组成的数组叫矩阵
x3=np.array([[1,2,3],[4,5,6],[7,8,9]])

# 张量的三个属性
# 个数（阶） x.ndim
# 形状 x.shape
# 数据类型 x.dtype

(train_images,train_labels),(test_images,test_labels)=mnist.load_data()
digit=train_images[4]
plt.imshow(digit,cmap=plt.cm.binary)
plt.show()


#relu 实现
def naive_relu(x):
    assert len(x.shape)==2

    x=x.copy()
    for i in range(x.shape[0]):
        for j in range(x.shape[1]):
            x[i,j]=max(x[i,j],0)
    return x

#add 实现
def naive_add(x,y):
    assert len(x.shape==2)
    assert x.shape==y.shape

    x=x.copy()
    for i in range(x.shape[0]):
        for j in range(x.shape[1]):
            x[i,j]+=y[i,j]
    return x