动手学pytorch第一天

一 线性回归

1 以前存在的知识误区

1_1假如你正在实现一个全连接层，全连接层的输入形状是7×8，输出形状是7×1，其中7是批量大小，则权重参数w和偏置参数b的形状分别是_8x1___和_ 1x1___

答：根据广播机制 当b.shape = (1,1)时 所有Xw加上的才是同一个bias

1_2 y_hat的形状是[n, 1]，而y的形状是[n]，两者相减得到的结果的形状是[n, n]，相当于用y_hat的每一个元素分别减去y的所有元素，所以无法得到正确的损失值。

2 具体流程

导包
# import packages and modules
%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

print(torch.__version__)

生成数据集
In [6]:

# set input feature number 
num_inputs = 2
# set example number
num_examples = 1000

# set true weight and bias in order to generate corresponded label
true_w = [2, -3.4]
true_b = 4.2

features = torch.randn(num_examples, num_inputs,
                      dtype=torch.float32)
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.float32)

读取数据
def data_iter(batch_size, features, labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    random.shuffle(indices)  # random read 10 samples
    for i in range(0, num_examples, batch_size):
        j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)]) # the last time may be not enough for a whole batch
        yield  features.index_select(0, j), labels.index_select(0, j)

初始化模型参数
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)), dtype=torch.float32)
b = torch.zeros(1, dtype=torch.float32)

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

定义模型
def linreg(X, w, b):
    return torch.mm(X, w) + b

定义损失函数
def squared_loss(y_hat, y): 
    return (y_hat - y.view(y_hat.size())) ** 2 / 2

定义优化函数
def sgd(params, lr, batch_size): 
    for param in params:
        param.data -= lr * param.grad / batch_size 

训练
lr = 0.03
num_epochs = 5

net = linreg
loss = squared_loss

# training
for epoch in range(num_epochs):  # training repeats num_epochs times
    # in each epoch, all the samples in dataset will be used once
    
    # X is the feature and y is the label of a batch sample
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y).sum()  
        # calculate the gradient of batch sample loss 
        l.backward()  
        # using small batch random gradient descent to iter model parameters
        sgd([w, b], lr, batch_size)  
        # reset parameter gradient
        w.grad.data.zero_()
        b.grad.data.zero_()
    train_l = loss(net(features, w, b), labels)
    print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))

学到的新函数

读取数据
读取数据集¶



    
    
In [18]:

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
    num_workers=2,              # read data in multithreading
)

初始化模型
from torch.nn import init

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