Pytorch学习笔记（二）
发布时间
阅读量：
阅读量
（3）批训练包装器DataLoader
Pytorch 中提供了一种帮你整理你的数据结构的好东西, 叫做 DataLoader, 我们能用它来包装自己的数据, 进行批训练.
import torch
import torch.utils.data as Data
BATCH_SIZE = 5
x = torch.linspace(1, 10, 10)
y = torch.linspace(10, 1, 10)
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
loader = Data.DataLoader(
dataset=torch_dataset,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=2
)
for epoch in range(3):
for step, (batch_x, batch_y) in enumerate(loader):
print("Epoch: ", epoch, " | Step: ", step, " | batchx: ", batch_x.numpy(), " | batchy: ", batch_y.numpy())运行结果如下：
Epoch: 0 | Step: 0 | batchx: [ 6. 5. 1. 9. 3.] | batchy: [ 5. 6. 10. 2. 8.]
Epoch: 0 | Step: 1 | batchx: [ 10. 2. 7. 8. 4.] | batchy: [ 1. 9. 4. 3. 7.]
Epoch: 1 | Step: 0 | batchx: [ 6. 5. 4. 7. 9.] | batchy: [ 5. 6. 7. 4. 2.]
Epoch: 1 | Step: 1 | batchx: [ 1. 8. 3. 10. 2.] | batchy: [ 10. 3. 8. 1. 9.]
Epoch: 2 | Step: 0 | batchx: [ 5. 6. 7. 9. 3.] | batchy: [ 6. 5. 4. 2. 8.]
Epoch: 2 | Step: 1 | batchx: [ 10. 4. 8. 1. 2.] | batchy: [ 1. 7. 3. 10. 9.]（4）使用ConvNet训练cifar-10数据集
# -*- coding:utf-8 -*-
import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
import torch.utils.data as Data
import matplotlib.pyplot as plt
import numpy as np
import time
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))]
)
trainset = torchvision.datasets.CIFAR10(
root='./data',
train=True,
transform=transform,
download=True,
)
trainloader = Data.DataLoader(
dataset=trainset,
batch_size= 4,
shuffle=True,
num_workers=4
)
testset = torchvision.datasets.CIFAR10(
root='./data',
train=False,
transform=transform,
download=True,
)
testloader = Data.DataLoader(
dataset=testset,
batch_size=4,
shuffle=False,
num_workers=4
)
def imshow(img):
img = img / 2 + 0.5
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
dataiter = iter(trainloader)
images, labels = dataiter.next()
print(images.size())
imshow(torchvision.utils.make_grid(images))
plt.show()
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def printnorm(self, input, output):
print('Inside ' + self.__class__.__name__ + ' forward')
print('')
print('input: ', type(input))
print('input[0]: ', type(input[0]))
print('output: ', type(output))
print('')
print('input size:', input[0].size())
print('output size:', output.data.size())
print('output norm:', output.data.norm())
net = Net().cuda()
# net.conv2.register_forward_hook(printnorm)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
start_time = time.time()
for epoch in range(2): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs
inputs, labels = data
# wrap them in Variable
inputs, labels = Variable(inputs).cuda(), Variable(labels).cuda()
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.data[0]
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0
print('Finished Training')
end_time = time.time()
print("Spend time:", end_time - start_time)
训练结果如下：
Files already downloaded and verified
Files already downloaded and verified
torch.Size([4, 3, 32, 32])
[1, 2000] loss: 2.204
[1, 4000] loss: 1.822
[1, 6000] loss: 1.705
[1, 8000] loss: 1.591
[1, 10000] loss: 1.524
[1, 12000] loss: 1.450
[2, 2000] loss: 1.402
[2, 4000] loss: 1.353
[2, 6000] loss: 1.344
[2, 8000] loss: 1.338
[2, 10000] loss: 1.286
[2, 12000] loss: 1.276
Finished Training
Spend time: 53.437838077545166（5）模型的保存与获取：
有时候训练网络需要大量的时间，所以训练好网络之后需要将它保存下来方便下次的使用，在Pytorch中有两种保存网络的方式，其中一种既保存了网络的结构，还保存了网络训练好的参数；另外一种方式只保存了网络训练好的参数，所以在下一次加载该网络参数的时候需要先对网络的结构进行定义。代码如下所示：
# -*- coding:utf-8 -*-
import torch
from torch.autograd import Variable
import torch.nn as nn
torch.manual_seed(1) # reproducible
# 假数据
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1) # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size()) # noisy y data (tensor), shape=(100, 1)
x, y = Variable(x, requires_grad=False), Variable(y, requires_grad=False)
def save():
# 建网络
net1 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1)
)
optimizer = torch.optim.SGD(net1.parameters(), lr=0.5)
loss_func = torch.nn.MSELoss()
# 训练
for t in range(100):
prediction = net1(x)
loss = loss_func(prediction, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
torch.save(net1, 'net.pkl') # 保存整个网络
torch.save(net1.state_dict(), 'net_params.pkl') # 只保存网络中的参数 (速度快, 占内存少)
def restore_net():
# restore entire net1 to net2
net2 = torch.load('net.pkl')
prediction = net2(x)
def restore_params():
# 新建 net3
net3 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
torch.nn.Linear(10, 1)
)
# 将保存的参数复制到 net3
net3.load_state_dict(torch.load('net_params.pkl'))
prediction = net3(x)全部评论 (0)
还没有任何评论哟~