我们将本书中经常导⼊和引⽤的函数、类等封装在d2l包中。
import collections #提供有关集合的操作
import hashlib #提供字符串加密的功能
import math
import os #处理文件和目录
import random
import re #正则表达式
import shutil #复制、移动、删除、压缩、解压文件
import sys #与python解释器交互的一个接口
import tarfile #压缩
import zipfile #解压
import time
from collections import defaultdict #当字典里的元素不存在但被查找时,返回一个默认值
import pandas as pd #利用series和dataframe进行数据处理
import requests #解码来自服务器的响应
from IPython import display #显示图片
from matplotlib import pyplot as plt #绘图
from matplotlib_inline import backend_inline #
d2l = sys.modules[__name__]
从
PyTorch
导⼊模块。
import numpy as np
import torch
import torchvision
from PIL import Image
from torch import nn
from torch.nn import functional as F
from torch.utils import data
from torchvision import transforms
import random
import torch
from d2l import torch as d2l
def synthetic_data(w, b, num_examples):
X = torch.normal(0, 1, (num_examples, len(w))) #均值为0,方差为1,大小为n个样本,列数为w的长度
y = torch.matmul(X, w) + b #y = Xw + b
y += torch.normal(0, 0.01, y.shape) #均值为0,方差为0.1(标准差为0.01),形状和y相同,y = Xw + b + 噪声
return X, y.reshape((-1, 1)) #以列向量返回
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)
print('features:',features[0],'\nlabel:',labels[0])
d2l.set_figsize()
d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
d2l.plt.show()
import random
import torch
from d2l import torch as d2l
def synthetic_data(w, b, num_examples):
X = torch.normal(0, 1, (num_examples, len(w)))
y = torch.matmul(X, w) + b
y += torch.normal(0, 0.01, y.shape)
return X, y.reshape((-1, 1))
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)
print('features:',features[0],'\nlabel:',labels[0])
d2l.set_figsize()
d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
d2l.plt.show()
def data_iter(batch_size,features,labels):
num_examples = len(features)
indices = list(range(num_examples))
random.shuffle(indices)
for i in range(0,num_examples,batch_size):
batch_indices = torch.tensor(indices[i:min(i+batch_size,num_examples)])
yield features[batch_indices], labels[batch_indices]
batch_size = 10
for X, y in data_iter(batch_size,features,labels):
print(X, '\n', y)
break
import random
import torch
from d2l import torch as d2l
def synthetic_data(w, b, num_examples):
X = torch.normal(0, 1, (num_examples, len(w))) #均值为0,方差为1,大小为n个样本,列数为w的长度
y = torch.matmul(X, w) + b #y = Xw + b
y += torch.normal(0, 0.01, y.shape) #均值为0,方差为0.1(标准差为0.01),形状和y相同,y = Xw + b + 噪声
return X, y.reshape((-1, 1)) #以列向量返回
true_w = torch.tensor([2, -3.4])
true_b = 4.2
features, labels = synthetic_data(true_w, true_b, 1000)
print('features:',features[0],'\nlabel:',labels[0])
d2l.set_figsize()
d2l.plt.scatter(features[:,1].detach().numpy(),labels.detach().numpy(),1)
d2l.plt.show()
def data_iter(batch_size,features,labels):
num_examples = len(features)
indices = list(range(num_examples)) #生成样本的index
random.shuffle(indices) #打乱
for i in range(0,num_examples,batch_size):
batch_indices = torch.tensor(indices[i:min(i+batch_size,num_examples)])
yield features[batch_indices], labels[batch_indices]
batch_size = 10
for X, y in data_iter(batch_size,features,labels):
print(X, '\n', y)
break
w = torch.normal(0,0.01,size = (2,1),requires_grad = True)
b = torch.zeros(1,requires_grad = True)
def linreg(X,w,b):
return torch.matmul(X,w) + b
def squard_loss(y_hat,y):
return(y_hat - y.reshape(y_hat.shape)) ** 2 / 2
def sgd(params,lr,batch_size):
with torch.no_grad():
for param in params:
param += -lr * param.grad / batch_size
param.grad.zero_()
lr = 0.03
num_epochs = 3
net = linreg
loss = squard_loss
for epoch in range(num_epochs):
for X,y in data_iter(batch_size,features,labels):
l = loss(net(X,w,b),y)
l.sum().backward()
sgd([w,b],lr,batch_size)
with torch.no_grad():
train_1 = loss(net(features,w,b),labels)
print(f'epoch{epoch + 1},loss{float(train_1.mean()):f}')
print(f'w的误差估计:{true_w - w.reshape(true_w.shape)}')
print(f'b的误差估计:{true_b - b}')
线性回归的简洁实现
import torch
from torch import nn
from torch.utils import data
from d2l import torch as d2l
true_w = torch.tensor([2,-3.4])
true_b = 4.2
features,labels = d2l.synthetic_data(true_w,true_b,1000)
def load_array(data_array,batch_size,is_train = True):
dataset = data.TensorDataset(*data_array)
return data.DataLoader(dataset,batch_size,shuffle = is_train)
batch_size = 10
data_iter = load_array((features,labels),batch_size)
print(next(iter(data_iter))[0])
print(next(iter(data_iter))[0])
net = nn.Sequential(nn.Linear(2,1)) #指定输入输出的维度
net[0].weight.data.normal_(0,0.01)
net[0].bias.data.fill_(0)
loss = nn.MSELoss()
trainer = torch.optim.SGD(net.parameters(),lr = 0.03)
num_epochs = 3
for epoch in range(num_epochs):
for X,y in data_iter:
l = loss(net(X),y) #前向传播
trainer.zero_grad() #梯度置0
l.backward() #计算梯度
trainer.step() #模型更新
l = loss(net(features),labels)
print(f'epoch{epoch + 1},loss{l:f}')
图像分类数据集
import torch
import torchvision
from torch.utils import data
from torchvision import transforms
from d2l import torch as d2l
d2l.use_svg_display()
trans = transforms.ToTensor() #转为tensor
mnist_train = torchvision.datasets.FashionMNIST(root = "../Data",train = True,transform = trans,download = True)
mnist_test = torchvision.datasets.FashionMNIST(root = "../Data",train = False,transform = trans,download = True)
print(len(mnist_train))
print(len(mnist_test))
print(mnist_train[0][0].shape)
def get_fashion_mnist_labels(labels):
text_labels = ['t-shirt','trouser','pullover','dress','coat','sandal','shirt','sneaker','bag','ankle boot']
return [text_labels[int(i)] for i in labels]
def show_images(imgs,num_rows,num_cols,titles = None,scale = 1.5):
figsize = (num_cols * scale,num_rows * scale)
_,axes = d2l.plt.subplots(num_rows,num_cols,figsize = figsize)
axes = axes.flatten()
for i,(ax,img) in enumerate(zip(axes,imgs)):
if torch.is_tensor(img):
ax.imshow(img.numpy(),'gray')
""""""
ax.axis('off')
ax.set_title(titles[i])
else:
ax.imshow(img)
d2l.plt.show()
X,y = next(iter(data.DataLoader(mnist_train,batch_size = 18)))
show_images(X.reshape(18,28,28),2,9,titles = get_fashion_mnist_labels(y))
batch_size = 256
def get_dataloader_workers():
return 4 #4个进程来进行读取
train_iter = data.DataLoader(mnist_train,batch_size,shuffle = True,num_workers = get_dataloader_workers())
timer = d2l.Timer()
for X,y in train_iter:
continue
print(f'{timer.stop():.2f}sec')
def load_data_fashion_mnist(batch_size,resize = None):
trans = [transforms.ToTensor()]
if resize:
trans.insert(0,transforms.Resize(resize))
trans = transforms.Compose(trans)
mnist_train = torchvision.datasets.FashionMNIST(root = "../Data",train = True,transform = trans,download = True)
mnist_test = torchvision.datasets.FashionMNIST(root = "../Data",train = False,transform = trans,download = True)
return (data.DataLoader(mnist_train,batch_size,shuffle = True,num_workers = get_dataloader_workers()),
data.DataLoader(mnist_test,batch_size,shuffle = True,num_workers = get_dataloader_workers()))
softmax回归的从0开始实现
import torch
from IPython import display
from d2l import torch as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
num_inputs = 784
num_outputs = 10
W = torch.normal(0,0.01,size=(num_inputs, num_outputs),requires_grad=True)
b = torch.zeros(num_outputs,requires_grad=True)
def softmax(X):
X_exp = torch.exp(X)
partition = X_exp.sum(1, keepdim=True) # 输入的X为矩阵,所以就是对矩阵每一行做Softmax
return X_exp / partition
X = torch.normal(0, 1, (2, 5))
X_prob = softmax(X)
print(X_prob)
print(X_prob.sum(1))
def net(X):
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)
X = torch.normal(0, 1, (2, 5))
print(X)
print(X + 1)
y = torch.tensor([0,2])
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
print(y_hat[[0, 1], y])
def cross_entropy(y_hat, y):
return -torch.log(y_hat[range(len(y_hat)), y])
def accuracy(y_hat, y):
if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
y_hat = y_hat.argmax(axis=1)
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
print(accuracy(y_hat, y))
class Accumulator:
def __init__(self, n):
self.data = [0.0] * n
def add(self, *args):
self.data = [a + float(b) for a, b in zip(self.data, args)]
def reset(self):
self.data = [0.0] * len(self.data)
def __getitem__(self, idx):
return self.data[idx]
def evaluate_accuracy(net, data_iter):
if isinstance(net, torch.nn.Module):
net.eval()
metric = Accumulator(2)
for X, y in data_iter:
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
def train_epoch_ch3(net, train_iter, loss, updater):
if isinstance(net, torch.nn.Module):
net.train()
metric = Accumulator(3)
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):
updater.zero_grad()
l.backward()
updater.step()
metric.add(float(l) * len(y), accuracy(y_hat, y), y.size().numel())
else :
l.sum().backward()
updater(X.shape[0])
metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
return metric[0] / metric[2] , metric[1] / metric[2]
class Animator:
def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
ylim=None, xscale='linear', yscale='linear',
fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
figsize=(3.5, 2.5)):
if legend is None:
legend = []
d2l.use_svg_display()
self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
if nrows * ncols == 1:
self.axes = [self.axes, ]
self.config_axes = lambda: d2l.set_axes(
self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
self.X, self.Y, self.fmts = None, None, fmts
def add(self, x, y):
if not hasattr(y, "__len__"):
y = [y]
n = len(y)
if not hasattr(x, "__len__"):
x = [x] * n
if not self.X:
self.X = [[] for _ in range(n)]
if not self.Y:
self.Y = [[] for _ in range(n)]
for i, (a, b) in enumerate(zip(x, y)):
if a is not None and b is not None:
self.X[i].append(a)
self.Y[i].append(b)
self.axes[0].cla()
for x, y, fmt in zip(self.X, self.Y, self.fmts):
self.axes[0].plot(x, y, fmt)
self.config_axes()
display.display(self.fig)
display.clear_output(wait=True)
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9],
legend=['train loss', 'train acc', 'test acc'])
for epoch in range(num_epochs):
train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
test_acc = evaluate_accuracy(net, test_iter)
animator.add(epoch + 1, train_metrics + (test_acc,))
d2l.plt.show()
train_loss, train_acc = train_metrics
lr = 0.1
def updater(batch_size):
return d2l.sgd([W, b], lr, batch_size)
num_epoch = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epoch, updater)
def predict_ch3(net, test_iter, n=6):
for X, y in test_iter:
break
trues = d2l.get_fashion_mnist_labels(y)
preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))
titles = [true + '\n' +pred for true, pred in zip(trues, preds)]
d2l.show_images(X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])
d2l.plt.show()
predict_ch3(net, test_iter)
softmax的简洁实现