import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append('..')
import d2lzh_pytorch as d2l
import torchvision
import torchvision.transforms as transforms
定义和初始化模型
#与上一节同样的数据集以及批量大小
batch_size= 256
mnist_train= torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',download=True,train=True,transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',download=True,train=False,transform=transforms.ToTensor())
if sys.platform.startswith('win'):
num_worker=0 # 表示不用额外的进程来加速读取数据
else:
num_worker=4
train_iter = torch.utils.data.DataLoader(mnist_train,batch_size=batch_size,shuffle=True,num_workers=num_worker)
test_iter = torch.utils.data.DataLoader(mnist_test,batch_size=batch_size,shuffle=False,num_workers=num_worker)
softmax的输出层是一个全连接层，所以我们使用一个线性模块就可以，因为前面我们数据返回的每个batch的样本X的形状为(batch_size,1,28,28)，我们先用view()将X转化为(batch_size,784)才送入全连接层
num_inputs = 784
num_outputs = 10
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):
y = self.linear(x.view(x.shape[0],-1))
return y
net = LinearNet(num_inputs,num_outputs)
# 我们将形状转化的这个功能定义成一个FlattenLayer
class FlattenLayer(nn.Module):
def __init__(self):
super(FlattenLayer,self).__init__()
def forward(self,x):
return x.view(x.shape[0],-1)
from collections import OrderedDict
net = nn.Sequential(
OrderedDict(
[
('flatten',FlattenLayer()),
('linear',nn.Linear(num_inputs,num_outputs))
])
)
# 之前线性回归的是num_output是1
init.normal_(net.linear.weight,mean=0,std=0.01) init.constant_(net.linear.bias,val=0)
Parameter containing: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], requires_grad=True)
print(net)
Sequential( (flatten): FlattenLayer() (linear): Linear(in_features=784, out_features=10, bias=True) )
softamx和交叉熵损失函数
#pytorch提供了一个包括softmax预算和交叉熵损失计算的函数 loss = nn.CrossEntropyLoss()
定义优化算法
optimizer = torch.optim.SGD(net.parameters(),lr=0.1)
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
num_epochs, lr = 5, 0.1
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:
# 上节的代码optimizer is None,使用的手写的代码SGD
sgd(params, lr, batch_size)
else:
# optimizer 非None，
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, loss, num_epochs, batch_size, None, None,optimizer)
epoch 1, loss 0.0031, train acc 0.749, test acc 0.765 epoch 2, loss 0.0022, train acc 0.813, test acc 0.808 epoch 3, loss 0.0021, train acc 0.826, test acc 0.818 epoch 4, loss 0.0020, train acc 0.832, test acc 0.816 epoch 5, loss 0.0019, train acc 0.837, test acc 0.821