pytorch softmax回归从零开始实现

数据

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import time
import sys
import d21
import numpy as np

mnist_train =torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=True, download=True, transform=transforms.ToTensor())
mnist_test =torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=False, download=True, transform=transforms.ToTensor())

def get_fashion_mnist_labels(labels):
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress','coat','sandal', 'shirt', 'sneaker', 'bag', 'ankleboot']
    return [text_labels[int(i)] for i in labels]

def show_fashion_mnist(images, labels):
    d21.use_svg_display()
 # 这⾥的_表示我们忽略（不使⽤）的变量
    _, 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))

为10分类问题，图像数据大小为28*28。

基本设置

batch_size = 256
train_iter, test_iter = d21.load_data_fashion_mnist(batch_size)

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)

softmax函数

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

例子：softmax函数的作用，使得一行输入转化为，和为1的数，就相当于每个分类的概率。

定义模型

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

定义损失函数

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

准确率

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

训练及预测

训练

num_epochs, lr = 5, 0.1
# 本函数已保存在d2lzh包中⽅便以后使⽤
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:
                d21.sgd(params, lr, batch_size)
            else:
                optimizer.step() # “softmax回归的简洁实现”⼀节将⽤到
            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)

预测

X, y = next(iter(test_iter))

true_labels = d21.get_fashion_mnist_labels(y.numpy())
pred_labels =d21.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels,pred_labels)]
show_fashion_mnist(X[0:9], titles[0:9])