import torch
from IPython import display
from matplotlib import pyplot as plt
import random
import sys
import torchvision
import torchvision.transforms as transforms
from torch import nn
def use_svg_display():
# 用矢量图显示
display.set_matplotlib_formats('svg')
def set_figsize(figsize=(3.5, 2.5)):
use_svg_display()
# 设置图的尺寸
plt.rcParams['figure.figsize'] = figsize
# 每次返回batch_size（批量大小）个随机样本的特征和标签。
def data_iter(batch_size, features, labels):
num_examples = len(features)
indices = list(range(num_examples))
random.shuffle(indices) # 样本的读取顺序是随机的
for i in range(0, num_examples, batch_size):
j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)]) # 最后一次可能不足一个batch
yield features.index_select(0, j), labels.index_select(0, j)
def linreg(X, w, b): # 定义线性模型
return torch.mm(X, w) + b
def squared_loss(y_hat, y): # 定义损失函数
# 注意这里返回的是向量, 另外, pytorch里的MSELoss并没有除以 2
return (y_hat - y.view(y_hat.size())) ** 2 / 2
def sgd(params, lr, batch_size): # 定义优化算法，它通过不断迭代模型参数来优化损失函数。这里自动求梯度模块计算得来的梯度是一个批量样本的梯度和。我们将它除以批量大小来得到平均值。
for param in params:
param.data -= lr * param.grad / batch_size # 注意这里更改param时用的param.data
# 读取数据集的label名称
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]
# 在一行里画出多张图像和对应标签
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 load_data_fashion_mnist(batch_size=256):
mnist_train = torchvision.datasets.FashionMNIST(root='D:/workspace/pytorch-test', train=True, download=False, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='D:/workspace/pytorch-test', train=False, download=False, transform=transforms.ToTensor())
print(len(mnist_train), len(mnist_test))
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)
return train_iter, test_iter
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
def train_softmax(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))
class FlattenLayer(nn.Module):
def __init__(self):
super(FlattenLayer, self).__init__()
def forward(self, x): # x shape: (batch, *, *, ...)
return x.view(x.shape[0], -1)
