3.神经网络-深度学习入门

3.神经网络

深度学习入门
本文的文件和代码链接:github地址

1.激活函数

  1. sigmoid
    h ( x ) = 1 1 + e − x h(x) = \frac{1}{1 + e^{-x}} h(x)=1+ex1
def sigmod(x):
    return 1 / (1 + np.exp(-1 * x))
  1. ReLU

h ( x ) = { x : x > 0 0 : x ≤ 0 h(x) = \left\{ \begin{array}{lr} x & : x > 0\\ 0 & : x \le 0 \end{array} \right. h(x)={x0:x>0:x0

  1. softmax 函数(常用来分类)
    y k = e a k ∑ i = 1 n e a i y_k = \frac{e^{a_k}}{\sum_{i=1}^n e^{a_i}} yk=i=1neaieak
    需要关注:softmax需要进行指数运算,因此容易溢出
    解决方法:
    y k = e a k ∑ i = 1 n e a i = C ∗ e a k C ∗ ∑ i = 1 n e a i = e x p ( a k + l o g C ) ∗ ∑ i = 1 n e x p ( a i + l o g C ) = e x p ( a k + C ′ ) ∗ ∑ i = 1 n e x p ( a i + C ′ ) y_k = \frac{e^{a_k}}{\sum_{i=1}^n e^{a_i}} = \frac{C *e^{a_k}}{C * \sum_{i= 1}^n e^{a_i}} = \frac{exp(a_k + logC)}{* \sum_{i= 1}^n exp(a_i + logC)} = \frac{exp(a_k + C')}{* \sum_{i= 1}^n exp(a_i + C')} yk=i=1neaieak=Ci=1neaiCeak=i=1nexp(ai+logC)exp(ak+logC)=i=1nexp(ai+C)exp(ak+C)
    即在进行softmax指数运算的时候,加上或减去某个数,结果不变,因此可以减去输入信号中的最大值

softmax代码实现:

def softmax(a):
    c = np.max(a)
    return np.exp(a - c) / np.sum(np.exp(a - c))  # 利用了数组的广播机制

2. 使用mnist数据集进行推理

数据集导入

import sys, os
import numpy as np
# 为了导入父目录中的文件, 即将父目录加入到 sys.path(Python的搜索模块)的路径集中
sys.path.append(os.pardir)
# 其中 dataset.mnist 为dataset文件夹下的python文件,用来进行数据集的预处理
from dataset.mnist import load_mnist
# 下载数据集
(x_train, t_train), (x_test, t_test) =  load_mnist(normalize=True, flatten=True, one_hot_label=True)

显示mnist图像

img = x_train[0]
label = t_train[0]
# 将图像形状转为(1, 28, 28)
img = img.reshape(28, 28)
# 使用 matplotlib.pyplot 进行查看
import matplotlib.pyplot as plt
plt.imshow(img)

显示结果:
3.神经网络-深度学习入门_第1张图片

前向推理过程

函数定义:

import pickle
# 因为只是进行测试,所以只需要获取测试集的数据
def get_data():
    (x_train, t_train), (x_test, t_test) =  load_mnist(normalize=True, flatten=True, one_hot_label=True)
    return x_test, t_test
# 初始化网络,从文件中读取之前保存好的权重(因为此时还没有学习如何进行训练,只是进行推理,因此使用给定的参数进行推理)
def init_network(file_path):
    with open(file_path, 'rb') as f:
        network = pickle.load(f)
    return network

# 进行推理预测
def predict(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']

    a1 = np.dot(x, W1) + b1
    z1 = sigmod(a1)

    a2 = np.dot(z1, W2) + b2
    z2 = sigmod(a2)

    a3 = np.dot(z2, W3) + b3
    z3 = softmax(a3)

    return z3

进行推理:

# 进行推理
x, t = get_data()
network = init_network("sample_weight.pkl")

# cnt 统计预测正确的个数
cnt = 0
# 遍历每一个样本
for i in range(x.shape[0]):
    y = predict(network, x[i])
    h = np.argmax(y)    # 获取y中最大值的索引
    if h == np.argmax(t[i]):
        cnt += 1

# cnt 最终输出为 9352

3. 批处理

之前预测的过程中一次处理一个样本,现在考虑一次处理多个样本的情况,即批处理。
一次打包输入多张图片(一张图片是一个样本,多张图片就是多个样本),这种打包式的输入就被称为批。

# 进行推理
x, t = get_data()
network = init_network("sample_weight.pkl")

# batch_size 定义一批处理的样本数
batch_size = 100
# cnt 统计预测正确的个数
cnt = 0
# 遍历每一个样本
for i in range(0, x.shape[0], batch_size):
    y = predict(network, x[i:i+batch_size])
    h = np.argmax(y, axis = 1)    # 按照列, 获取y中每一行中最大值的索引(行不变,在列上计算, 因此axis=1)
    cnt += np.sum(h == np.argmax(t[i:i+batch_size], axis = 1))
# cnt仍然为 9352

4. 补充说明

dataset目录下 mnist.py 文件内容:

# coding: utf-8
try:
    import urllib.request
except ImportError:
    raise ImportError('You should use Python 3.x')
import os.path
import gzip
import pickle
import os
import numpy as np


url_base = 'http://yann.lecun.com/exdb/mnist/'
key_file = {
    'train_img':'train-images-idx3-ubyte.gz',
    'train_label':'train-labels-idx1-ubyte.gz',
    'test_img':'t10k-images-idx3-ubyte.gz',
    'test_label':'t10k-labels-idx1-ubyte.gz'
}

dataset_dir = os.path.dirname(os.path.abspath(__file__))
save_file = dataset_dir + "/mnist.pkl"

train_num = 60000
test_num = 10000
img_dim = (1, 28, 28)
img_size = 784


def _download(file_name):
    file_path = dataset_dir + "/" + file_name
    
    if os.path.exists(file_path):
        return

    print("Downloading " + file_name + " ... ")
    urllib.request.urlretrieve(url_base + file_name, file_path)
    print("Done")
    
def download_mnist():
    for v in key_file.values():
       #  其中 v 是 key_file 中的值, 不是key
       _download(v)    # 下载后文件名为 /train-images-idx3-ubyte.gz 等
        
def _load_label(file_name):
    file_path = dataset_dir + "/" + file_name
    
    print("Converting " + file_name + " to NumPy Array ...")
    with gzip.open(file_path, 'rb') as f:
            labels = np.frombuffer(f.read(), np.uint8, offset=8)
    print("Done")
    
    return labels

def _load_img(file_name):
    # 此时 file_path 为 /train-images-idx3-ubyte.gz等
    file_path = dataset_dir + "/" + file_name
    
    print("Converting " + file_name + " to NumPy Array ...")    
    with gzip.open(file_path, 'rb') as f:
            # np.frombuffer 将缓冲区解释为一维数组, 即将 /train-images-idx3-ubyte.gz 解释为一维数组
            data = np.frombuffer(f.read(), np.uint8, offset=16)
    data = data.reshape(-1, img_size)
    print("Done")
    
    return data

# 将下载后的对象转为 numpy
def _convert_numpy():
    dataset = {}
    dataset['train_img'] =  _load_img(key_file['train_img'])
    dataset['train_label'] = _load_label(key_file['train_label'])    
    dataset['test_img'] = _load_img(key_file['test_img'])
    dataset['test_label'] = _load_label(key_file['test_label'])
    
    return dataset

def init_mnist():
    download_mnist()
    dataset = _convert_numpy()
    print("Creating pickle file ...")
    with open(save_file, 'wb') as f:
        # 序列化操作,将对象dataset保存到 f 文件中,其中 f为 dataset_dir + "/mnist.pkl"
        pickle.dump(dataset, f, -1)
    print("Done!")

def _change_one_hot_label(X):
    T = np.zeros((X.size, 10))
    for idx, row in enumerate(T):
        row[X[idx]] = 1
        
    return T
    

def load_mnist(normalize=True, flatten=True, one_hot_label=False):
    """读入MNIST数据集
    
    Parameters
    ----------
    normalize : 将图像的像素值正规化为0.0~1.0
    one_hot_label : 
        one_hot_label为True的情况下,标签作为one-hot数组返回
        one-hot数组是指[0,0,1,0,0,0,0,0,0,0]这样的数组
    flatten : 是否将图像展开为一维数组
    
    Returns
    -------
    (训练图像, 训练标签), (测试图像, 测试标签)
    """
    if not os.path.exists(save_file):
        init_mnist()
        
    with open(save_file, 'rb') as f:
        dataset = pickle.load(f)
    
    if normalize:
        for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].astype(np.float32)
            dataset[key] /= 255.0
            
    if one_hot_label:
        dataset['train_label'] = _change_one_hot_label(dataset['train_label'])
        dataset['test_label'] = _change_one_hot_label(dataset['test_label'])
    
    if not flatten:
         for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].reshape(-1, 1, 28, 28)

    return (dataset['train_img'], dataset['train_label']), (dataset['test_img'], dataset['test_label']) 


if __name__ == '__main__':
    init_mnist()

你可能感兴趣的:(深度学习,深度学习,神经网络,python)