深度学习实战模拟——softmax回归（图像识别并分类）

1、数据集：

2、完整代码

1、数据集：

1.1 Fashion-MNIST是一个服装分类数据集，由10个类别的图像组成，分别为t-shirt（T恤）、trouser（裤子）、pullover（套衫）、dress（连衣裙）、coat（外套）、sandal（凉鞋）、shirt（衬衫）、sneaker（运动鞋）、bag（包）和ankle boot（短靴）。

1.2 Fashion‐MNIST由10个类别的图像组成，每个类别由训练数据集（train dataset）中的6000张图像和测试数据集（test dataset）中的1000张图像组成。因此，训练集和测试集分别包含60000和10000张图像。测试数据集不会用于训练，只用于评估模型性能。

以下函数用于在数字标签索引及其文本名称之间进行转换。

# 通过ToTensor实例将图像数据从PIL类型变换成32位浮点数格式，
# 并除以255使得所有像素的数值均在0～1之间
trans = transforms.ToTensor()
mnist_train = torchvision.datasets.FashionMNIST(root="../data", train=True, transform=trans, download=True)
mnist_test = torchvision.datasets.FashionMNIST(root="../data", train=False, transform=trans, download=True)

以下函数用于在数字标签索引及其文本名称之间进行转换。

def get_fashion_mnist_labels(labels):  #@save"""返回Fashion-MNIST数据集的文本标签"""text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat','sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']return [text_labels[int(i)] for i in labels]

2、完整代码

import torch
import torchvision
import pylab
from torch.utils import data
from torchvision import transforms
import matplotlib.pyplot as plt
from d2l import torch as d2l
import timebatch_size = 256
num_inputs = 784
num_outputs = 10
W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)
num_epochs = 5class Accumulator:"""在n个变量上累加"""def __init__(self, n):self.data = [0.0] * ndef add(self, *args):self.data = [a + float(b) for a, b in zip(self.data, args)]def reset(self):self.data = [0.0] * len(self.data)def __getitem__(self, idx):return self.data[idx]def accuracy(y_hat, y):  #@save"""计算预测正确的数量"""if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:y_hat = y_hat.argmax(axis=1)cmp = y_hat.type(y.dtype) == yreturn float(cmp.type(y.dtype).sum())def cross_entropy(y_hat, y):return -torch.log(y_hat[range(len(y_hat)), y])def softmax(X):X_exp = torch.exp(X)partition = X_exp.sum(1, keepdim=True)return X_exp/partitiondef net(X):return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)def get_dataloader_workers():"""使用一个进程来读取的数据"""return 1def get_fashion_mnist_labels(labels):"""返回Fashion-MNIST数据集的文本标签"""#共10个类别text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']return [text_labels[int(i)] for i in labels]def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5):"""画一系列图片"""figsize = (num_cols * scale, num_rows * scale)_, axes = plt.subplots(num_rows, num_cols, figsize=figsize)for i, (img, label) in enumerate(zip(imgs, titles)):xloc, yloc = i//num_cols, i % num_colsif torch.is_tensor(img):# 图片张量axes[xloc, yloc].imshow(img.reshape((28, 28)).numpy())else:# PIL图片axes[xloc, yloc].imshow(img)# 设置标题并取消横纵坐标上的刻度axes[xloc, yloc].set_title(label)plt.xticks([], ())axes[xloc, yloc].set_axis_off()pylab.show()def load_data_fashion_mnist(batch_size, resize=None):"""下载Fashion-MNIST数据集，然后将其加载到内存中"""trans = transforms.ToTensor()if resize:trans.insert(0, transforms.Resize(resize))mnist_train = torchvision.datasets.FashionMNIST(root='../data', train=True, transform=trans, download=True)mnist_test = torchvision.datasets.FashionMNIST(root='../data', train=False, transform=trans, download=True)return (data.DataLoader(mnist_train, batch_size, shuffle=True, num_workers=get_dataloader_workers()),data.DataLoader(mnist_test, batch_size, shuffle=False, num_workers=get_dataloader_workers()))def evaluate_accuracy(net, data_iter):"""计算在指定数据集上模型的精度"""if isinstance(net, torch.nn.Module):net.eval()  # 将模型设置为评估模式metric = Accumulator(2)  # 正确预测数、预测总数with torch.no_grad():for X, y in data_iter:metric.add(accuracy(net(X), y), y.numel())return metric[0] / metric[1]def updater(batch_size):lr = 0.1return d2l.sgd([W, b], lr, batch_size)def train_epoch_ch3(net, train_iter, loss, updater):if isinstance(net, torch.nn.Module):net.train()metric = Accumulator(3)for X, y in train_iter:y_hat = net(X)lo = loss(y_hat, y)if isinstance(updater, torch.optim.Optimizer):updater.zero_grad()lo.backward()updater.step()metric.add(float(lo)*len(y), accuracy(y_hat, y), y.size().numel())else:lo.sum().backward()updater(X.shape[0])metric.add(float(lo.sum()), accuracy(y_hat, y), y.numel())return metric[0] / metric[2], metric[1] / metric[2]class Animator:  #@save"""绘制数据"""def __init__(self, legend=None):self.legend = legendself.X = [[], [], []]self.Y = [[], [], []]def add(self, x, y):# 向图表中添加多个数据点if not hasattr(y, "__len__"):y = [y]n = len(y)if not hasattr(x, "__len__"):x = [x] * nfor i, (a, b) in enumerate(zip(x, y)):if a is not None and b is not None:self.X[i].append(a)self.Y[i].append(b)def show(self):plt.plot(self.X[0], self.Y[0], 'r--')plt.plot(self.X[1], self.Y[1], 'g--')plt.plot(self.X[2], self.Y[2], 'b--')plt.legend(self.legend)plt.xlabel('epoch')plt.ylabel('value')plt.title('Visual')plt.show()def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):  #@save"""训练模型"""animator = Animator(legend=['train loss', 'train acc', 'test acc'])for epoch in range(num_epochs):train_metrics = train_epoch_ch3(net, train_iter, loss, updater)train_loss, train_acc = train_metricstest_acc = evaluate_accuracy(net, test_iter)animator.add(epoch + 1, train_metrics + (test_acc,))print(f'epoch: {epoch+1},train_loss:{train_loss:.4f}, train_acc:{train_acc:.4f}, test_acc:{test_acc:.4f}')animator.show()def predict_ch3(net, test_iter, n=12):"""预测标签"""for X, y in test_iter:breaktrues = d2l.get_fashion_mnist_labels(y)preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))titles = [true +'\n' + pred for true, pred in zip(trues, preds)]show_images(X[0:n].reshape((n, 28, 28)), 2, int(n/2), titles=titles[0:n])if __name__ == '__main__':train_iter, test_iter = load_data_fashion_mnist(batch_size)train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)predict_ch3(net, test_iter)

分类效果：