# SoftMax实现图像分类

Posted 2021-09-09 tacit-lxs

SoftMax实现图像分类

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import time
import sys
# 一、加载数据
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 = 256
if 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 = 4
train_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)

def use_svg_display():
 # ⽤⽮量图显示
    display.set_matplotlib_formats('svg')
def set_figsize(figsize=(5.5, 2.5)):
    use_svg_display()
 # 设置图的尺⼨
    plt.rcParams['figure.figsize'] = figsize
def get_fashion_mnist_labels(labels):
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
                   'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
    return [text_labels[int(i)] for i in labels]
# 本函数已保存在d2lzh包中方便以后使用
def show_fashion_mnist(images, labels):
    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()
def softmax(X):
    X_exp = X.exp()
    partition = X_exp.sum(dim=1, keepdim=True)
    return X_exp / partition  # 这里应用了广播机制

# 二、参数模型初始化
num_inputs = 784 #由于图片大小为28x28共784个像素点
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)

# 三、模型定义
def net(X):
    return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)

# 四、损失函数
def cross_entropy(y_hat, y):
    return - torch.log(y_hat.gather(1, y.view(-1, 1)))
#精度
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

# 五、训练模型
num_epochs, lr = 5, 0.1

def sgd(params, lr, batch_size): # 本函数已保存在d2lzh_pytorch包中⽅便以后使⽤
    for param in params:
        param.data -= lr * param.grad / batch_size # 注意这⾥更改param时⽤的param.data
        

# 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:
                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)
#展示
X, y = iter(test_iter).next()

true_labels = get_fashion_mnist_labels(y.numpy())
pred_labels = 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])