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)

生成数据集

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, # torch TensorDataset format
batch_size=batch_size, # mini batch size
shuffle=True, # whether shuffle the data or not
num_workers=2, # read data in multithreading
)

for X, y in data_iter:
print(X, ‘\n’, y)
break

定义模型

class LinearNet(nn.Module):
def init(self, n_feature):
super(LinearNet, self).init() # call father function to init
self.linear = nn.Linear(n_feature, 1) # function prototype: torch.nn.Linear(in_features, out_features, bias=True)

def forward(self, x):
    y = self.linear(x)
    return y

net = LinearNet(num_inputs) # 模型实例化

参数初始化
from torch.nn import init

init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0)

loss = nn.MSELoss() #交叉熵损失函数
优化模型
import torch.optim as optim

optimizer = optim.SGD(net.parameters(), lr=0.03) # built-in random gradient descent function
print(optimizer)

模型训练
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() # reset gradient, equal to net.zero_grad()
l.backward()
optimizer.step()
print(‘epoch %d, loss: %f’ % (epoch, l.item()))

Softmax与分类模型
导入模块
import torch
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

获取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root=’/home/kesci/input/FashionMNIST2065’

超参数初始化
num_inputs = 784
print(28*28)
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)
自定义 SOFTMAX函数
def softmax(X):
X_exp = X.exp()
partition = X_exp.sum(dim=1, keepdim=True)
# print("X size is ", X_exp.size())
# print("partition size is ", partition, partition.size())
return X_exp / partition # 这里应用了广播机制
自定义模型
def net(X):
return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)

损失函数
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y = torch.LongTensor([0, 2])
y_hat.gather(1, y.view(-1, 1))

自定义准确率函数：

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

模型训练
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()

        # 梯度清零
        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()

多层感知机pytorch实现

导入模块
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

获取数据
atch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size,root=’/home/kesci/input/FashionMNIST2065’)
定义模型

num_inputs, num_outputs, num_hiddens = 784, 10, 256

W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)

params = [W1, b1, W2, b2]
for param in params:
param.requires_grad_(requires_grad=True)

激活函数
def relu(X):
return torch.max(input=X, other=torch.tensor(0.0))
定义网路 损失函数
def net(X):
X = X.view((-1, num_inputs))
H = relu(torch.matmul(X, W1) + b1)
return torch.matmul(H, W2) + b2

loss = torch.nn.CrossEntropyLoss()
模型训练
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)