# SoftMax实现图像分类
Posted tacit-lxs
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了# SoftMax实现图像分类相关的知识,希望对你有一定的参考价值。
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])
以上是关于# SoftMax实现图像分类的主要内容,如果未能解决你的问题,请参考以下文章
《计算机视觉和图像处理简介 - 中英双语版》:基于PyTorch Softmax 进行 MNIST 手写数字分类Digit Classification with Softmax
python逻辑回归(logistic regression LR) 底层代码实现 BGD梯度下降算法 softmax多分类