使用softmax回归实现对Fashion-MNIST数据集进行分类

import torchfrom torch import nnfrom torch.nn import initimport numpy as npimport sys

读取数据集：

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())batch_size = 256if sys.platform.startswith('win'):num_workers = 0 # 0表示不用额外的进程来加速读取数据else:num_workers = 4train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)

初始化模型：

num_inputs = 784num_outputs = 10class LinearNet(nn.Module):def __init__(self, num_inputs, num_outputs):super(LinearNet, self).__init__()self.linear = nn.Linear(num_inputs, num_outputs)def forward(self, x): # x shape: (batch, 1, 28, 28)y = self.linear(x.view(x.shape[0], -1))return ynet = LinearNet(num_inputs, num_outputs)# 初始化线性模型的参数init.normal_(net.linear.weight, mean=0, std=0.01)init.constant_(net.linear.bias, val=0) # 定义损失函数，包括softmax运算和交叉熵损失计算loss = nn.CrossEntropyLoss()# 定义优化算法optimizer = torch.optim.SGD(net.parameters(), lr=0.1)

训练模型：

num_epochs = 5def evaluate_accuracy(data_iter, net):acc_sum, n = 0.0, 0for X, y in data_iter:acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()n += y.shape[0]return acc_sum / ndef 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, 0for 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() # 这里我们用到优化器，所以直接对优化器行梯度清零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:sgd(params, lr, batch_size)else:optimizer.step() # 用到优化器这里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, loss, num_epochs, batch_size, None, None, optimizer)