参考链接
https://pytorch.org/tutorials/beginner/former_torchies/parallelism_tutorial.html#dataparallel
https://blog.csdn.net/wumo1556/article/details/89065916
使用多GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
if torch.cuda.device_count() > 1:
net = torch.nn.DataParallel(net)
net.to(device)
保存
PATH = './cifar_net.pth'
torch.save(net.module.state_dict(), PATH)
加载
net = Net().to(device)
net.load_state_dict(torch.load(PATH))
outputs = net(images)
模板
import matplotlib.pyplot as plt
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
criterion = nn.CrossEntropyLoss()
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
batch_size = 4
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Assuming that we are on a CUDA machine, this should print a CUDA device:
print(device)
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(batch_size)))
class Net(nn.Module):
def __init__(self):
super().__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 = torch.flatten(x, 1) # flatten all dimensions except batch
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
if torch.cuda.device_count() > 1:
print("Let's use", torch.cuda.device_count(), "GPUs!")
net = nn.DataParallel(net)
net.to(device)
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
for epoch in range(1): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data[0].to(device), data[1].to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
print("Outside: input size", inputs.size(), "output_size", outputs.size())
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
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')
PATH = './cifar_net.pth'
torch.save(net.module.state_dict(), PATH)
dataiter = iter(testloader)
images, labels = dataiter.next()
# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
net = Net().to(device)
net.load_state_dict(torch.load(PATH))
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))
correct = 0
total = 0
# since we're not training, we don't need to calculate the gradients for our outputs
with torch.no_grad():
for data in testloader:
# images, labels = data[0].to(device), data[1].to(device)
images, labels = data
# calculate outputs by running images through the network
outputs = net(images)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
# prepare to count predictions for each class
correct_pred = {
classname: 0 for classname in classes}
total_pred = {
classname: 0 for classname in classes}
# again no gradients needed
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predictions = torch.max(outputs, 1)
# collect the correct predictions for each class
for label, prediction in zip(labels, predictions):
if label == prediction:
correct_pred[classes[label]] += 1
total_pred[classes[label]] += 1
# print accuracy for each class
for classname, correct_count in correct_pred.items():
accuracy = 100 * float(correct_count) / total_pred[classname]
print("Accuracy for class {:5s} is: {:.1f} %".format(classname, accuracy))
# Time: 2021/8/26 16:00
# Software: PyCharm
# Description: train
import torch
# todo 数据
class CjDataset(torch.utils.data.Dataset):
def __init__(self):
pass
def __len__(self):
# todo 返回长度
pass
def __getitem__(self, index):
# todo 某个image以及他的标签
pass
dataset = CjDataset()
train_loader = torch.utils.data.DataLoader(dataset, batch_size=16, shuffle=True, num_work=2, drop_last=False)
# todo 模型
class CjModule(torch.nn.Module):
def __init__(self):
super(self).__init__()
pass
def forward(self, x):
# todo 网络
pass
net = CjModule()
# todo GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
if torch.cuda.device_count() > 1:
net = torch.nn.DataParallel(net)
net.to(device)
# todo train
error = 0
for epoch in range(100):
for data in train_loader:
inputs, labels = data[0].to(device), data[1].to(device)
outputs = net(inputs)
error += 1
pass
print(error)