欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

[pytorch、学习] - 3.6 softmax回归的从零开始实现

程序员文章站 2022-05-26 20:45:41
...

参考

3.6 softmax回归的从零开始实现

import torch
import torchvision
import numpy as np
import sys
sys.path.append("..")
import d2lzh_pytorch as d2l

3.6.1. 获取和读取数据

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

3.6.2. 初始化模型参数

num_inputs = 784
num_outputs = 10

W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float)  # torch.Size([784, 10])
b = torch.zeros(num_outputs, dtype=torch.float)   # torch.Size([10])

# 同之前一样,我们需要模型参数梯度。
W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)

[pytorch、学习] - 3.6 softmax回归的从零开始实现

3.6.3. 实现softmax运算

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

3.6.4. 定义模型

# 传入特征,给出预测值
def net(X):
    return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)

3.6.5. 定义损失函数

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

3.6.6. 计算分类准确率

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

3.6.7. 训练模型

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()

            # 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()  # “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)

[pytorch、学习] - 3.6 softmax回归的从零开始实现

3.6.8. 预测

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])

[pytorch、学习] - 3.6 softmax回归的从零开始实现