Pytorch学习

线性回归

import torch
from torch import nn
import numpy as np

torch.manual_seed(1)#生成随机数种子，确保每次得到的随机数一致

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 #严格意义上的标签
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)
#正态分布生成偏差用来模拟真实数据

import torch.utils.data as Data

batch_size = 10

# combine featues and labels of dataset
dataset = Data.TensorDataset(features, labels)

# put dataset into DataLoader
data_iter = Data.DataLoader(
    dataset=dataset,            # torch TensorDataset format
    batch_size=batch_size,      # mini batch size
    shuffle=True,               # whether shuffle the data or not #将数据无序放置
    num_workers=2,              # read data in multithreading
)

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

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)
print(net)

#三种构建模型的方式
# ways to init a multilayer network
# method one
net = nn.Sequential(
    nn.Linear(num_inputs, 1)
    # other layers can be added here
    )

# method two
net = nn.Sequential()
net.add_module('linear', nn.Linear(num_inputs, 1))
# net.add_module ......

# method three
from collections import OrderedDict
net = nn.Sequential(OrderedDict([
          ('linear', nn.Linear(num_inputs, 1))
          # ......
        ]))

print(net)
print(net[0]) #此时网络什么都没有

from torch.nn import init

#权重与偏置的定义
init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0)  # or you can use `net[0].bias.data.fill_(0)` to modify it directly

for param in net.parameters():
    print(param)

loss = nn.MSELoss()    # nn built-in squared loss function
                       # function prototype: `torch.nn.MSELoss(size_average=None, #reduce=None, reduction='mean')`

import torch.optim as optim

optimizer = optim.SGD(net.parameters(), lr=0.03)   # built-in random gradient descent function
print(optimizer)  # function prototype: `torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)`

num_epochs = 3
for epoch in range(1, num_epochs + 1):
    for X, y in data_iter:
        output = net(X) #前面构建的网络模型
        l = loss(output, y.view(-1, 1)) #计算预测值与真实值的差距
        optimizer.zero_grad() # reset gradient, equal to net.zero_grad() #重置梯度，防止梯度叠加
        l.backward() #反向传播计算梯度
        optimizer.step() #权重与偏置的更新
    print('epoch %d, loss: %f' % (epoch, l.item()))

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

 下一步是学习__init__，forward()函数的使用