Task1.0 学习笔记线性回归；Softmax与分类模型、多层感知机

线性回归模型使用pytorch的简洁实现

import torch
from torch import nn
import numpy as np
torch.manual_seed(1)

print(torch.version)
torch.set_default_tensor_type(‘torch.FloatTensor’)

#生成数据
num_inputs = 2
num_examples = 1000

true_w = [2, -3.4]
true_b = 4.2

features = torch.tensor(np.random.normal(0, 1, (num_examples, num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)

#读取数据
import torch.utils.data as Data

batch_size = 10
dataset = Data.TensorDataset(features, labels)
data_iter = Data.DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True, num_workers=2)

#模型
class LinearNet(nn.Module):
	def init(self, n_feature):
		super(LinearNet, self).init()
		self.linear = nn.Linear(n_feature, 1)
	def forward(self, x):
    	y = self.linear(x)
    	return y

net = LinearNet(num_inputs)
#net = nn.Sequential(nn.Linear(num_inputs, 1))
#
#net = nn.Sequential()
#net.add_module(‘linear’, nn.Linear(num_inputs, 1))
#
#from collections import OrderedDict
#net = nn.Sequential(OrderedDict([(‘linear’, nn.Linear(num_inputs, 1))]))

#初始化模型参数
from torch.nn import init

init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0) 
# net[0].bias.data.fill_(0) 
#for param in net.parameters():
#	print(param)

#损失函数
loss = nn.MSELoss()

#优化函数
import torch.optim as optim

optimizer = optim.SGD(net.parameters(), lr=0.03)
#print(optimizer)

#训练
num_epochs = 3
for epoch in range(1, num_epochs + 1):
	for X, y in data_iter:
		output = net(X)
		l = loss(output, y.view(-1, 1))
		optimizer.zero_grad() 
		# net.zero_grad()
		l.backward()
		optimizer.step()
	print(‘epoch %d, loss: %f’ % (epoch, l.item()))

dense = net[0]
print(true_w, dense.weight.data)
print(true_b, dense.bias.data)

获取Fashion-MNIST训练集和读取数据

服务于PyTorch深度学习框架的torchvision组成：

1. torchvision.datasets: 一些加载数据的函数及常用的数据集接口；
2. torchvision.models: 包含常服务于PyTorch深度学习框架的用的模型结构（含预训练模型），例如AlexNet、VGG、ResNet等；
3. torchvision.transforms: 常用的图片变换，例如裁剪、旋转等；
4. torchvision.utils: 其他的一些有用的方法。

%matplotlib inline
from IPython import display
import matplotlib.pyplot as plt

import torch
import torchvision
import torchvision.transforms as transforms
import time

import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

print(torch.version)
print(torchvision.version)

#获取数据集
mnist_train = torchvision.datasets.FashionMNIST(root=’/home/kesci/input/FashionMNIST2065’, train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root=’/home/kesci/input/FashionMNIST2065’, train=False, download=True, transform=transforms.ToTensor())

print(type(mnist_train))
print(len(mnist_train), len(mnist_test))

feature, label = mnist_train[0]
print(feature.shape, label) 

mnist_PIL = torchvision.datasets.FashionMNIST(root=’/home/kesci/input/FashionMNIST2065’, train=True, download=True)
PIL_feature, label = mnist_PIL[0]
print(PIL_feature)

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_fashion_mnist(images, labels):
    d2l.use_svg_display()
    _, figs = plt.subplots(1, len(images), figsize=(12, 12))
    for f, img, lbl in zip(figs, images, labels):
        f.imshow(img.view((28, 28)).numpy())
        f.set_title(lbl)
        f.axes.get_xaxis().set_visible(False)
        f.axes.get_yaxis().set_visible(False)
    plt.show()

X, y = [], []
for i in range(10):
    X.append(mnist_train[i][0]) 
    y.append(mnist_train[i][1]) 
show_fashion_mnist(X, get_fashion_mnist_labels(y))

# 读取数据
batch_size = 256
num_workers = 4
train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)

start = time.time()
for X, y in train_iter:
    continue
print('%.2f sec' % (time.time() - start))

softmax从零开始的实现

import torch
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root='/home/kesci/input/FashionMNIST2065')

num_inputs = 784
num_outputs = 10

W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float)
b = torch.zeros(num_outputs, dtype=torch.float)

W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)

def softmax(X):
    X_exp = X.exp()
    partition = X_exp.sum(dim=1, keepdim=True)
    return X_exp / partition  

def net(X):
    return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)

def cross_entropy(y_hat, y):
    return - torch.log(y_hat.gather(1, y.view(-1, 1)))

def accuracy(y_hat, y):
    return (y_hat.argmax(dim=1) == y).float().mean().item()

def evaluate_accuracy(data_iter, net):
    acc_sum, n = 0.0, 0
    for X, y in data_iter:
        acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
        n += y.shape[0]
    return acc_sum / n


num_epochs, lr = 5, 0.1
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
              params=None, lr=None, optimizer=None):
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for X, y in train_iter:
            y_hat = net(X)
            l = loss(y_hat, y).sum()
            
            if optimizer is not None:
                optimizer.zero_grad()
            elif params is not None and params[0].grad is not None:
                for param in params:
                    param.grad.data.zero_()
            
            l.backward()
            if optimizer is None:
                d2l.sgd(params, lr, batch_size)
            else:
                optimizer.step() 
            
            
            train_l_sum += l.item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
            n += y.shape[0]
        test_acc = evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
              % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size, [W, b], lr)

X, y = iter(test_iter).next()

true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]

d2l.show_fashion_mnist(X[0:9], titles[0:9])

简洁实现

class LinearNet(nn.Module):
    def __init__(self, num_inputs, num_outputs):
        super(LinearNet, self).__init__()
        self.linear = nn.Linear(num_inputs, num_outputs)
    def forward(self, x): 
        y = self.linear(x.view(x.shape[0], -1))
        return y

class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer, self).__init__()
    def forward(self, x): 
        return x.view(x.shape[0], -1)

from collections import OrderedDict
net = nn.Sequential(
        OrderedDict([
           ('flatten', FlattenLayer()),
           ('linear', nn.Linear(num_inputs, num_outputs))]) 
        )
init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)
loss = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.1)