学习教材:
动手学深度学习 PYTORCH 版(DEMO)
(https://github.com/ShusenTang/Dive-into-DL-PyTorch)
PDF 制作by [Marcus Yang](https://github.com/chenyang1999)
直接代码:
'''导入所需的包'''
import torch
from torch import nn
from torch.nn import init
import numpy as np
import torchvision
# 下载并读取数据集
def load_data_fashion_mnist(batch_size, resize=None, root='~/Datasets/FashionMNIST'):
"""Download the fashion mnist dataset and then load intomemory."""
trans = []
if resize:
trans.append(torchvision.transforms.Resize(size=resize))
trans.append(torchvision.transforms.ToTensor())
transform = torchvision.transforms.Compose(trans)
mnist_train = torchvision.datasets.FashionMNIST(root=root, train=True, download=True, transform=transform)
mnist_test = torchvision.datasets.FashionMNIST(root=root,
train=False, download=True, transform=transform)
train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=4)
test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=4)
return train_iter, test_iter
''' 获取和读取数据 '''
batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)
''' 定义和初始化模型'''
num_inputs = 784
num_outputs = 10
# 定义线性模型
class 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 y
# 定义一个FlatternLayer,用作对x的形状转换的这个功能。
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)
net = LinearNet(num_inputs, num_outputs)
from collections import OrderedDcit
net = nn.Sequential(
OrderedDict([
('flatten', FlattenLayer()),
('linear', nn.Linear(num_inputs, num_outputs))
])
)
# 然后我们使用均值为0,标准差为0.01的正态随机初始化模型的权重参数。
init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)
# pytorch提供一个包含softmax和交叉熵损失函数计算的函数,它的数值稳定性更高。
loss = nn.CrossEntropyLoss()
# 使用学习率为0.1的小批量随机梯度下降算法作为优化函数
optimizer = torch.optim.SGD(net.parameters(), lr=0.1)
def sgd(params, lr, batch_size):
for param in params:
param.data -= lr * param.grad / batch_size
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
# 训练模型
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()
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))
num_epochs = 5
train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)