import numpy as np
import torch
a = np.ones(5)
b = torch.from_numpy(a)
np.add(a, 1, out = a)
if torch.cuda.is_available():
device = torch.device("cuda")
c = torch.ones_like(b, device = device)
x = torch.ones(2, 2, requires_grad = True)
y = x + 2
z = y * y * 3
out = z.mean()
a = torch.randn(2, 2)
print(a)
a.requires_grad_(True)
b = a.sum()
out.backward(retain_graph = True)
x = torch.rand(3, requires_grad = True)
y = x * x
while y.data.norm() < 1000:
y = y * 2
with torch.no_grad():
print((x ** 2).requires_grad)
import torch.nn as nn
import torch.nn.functional as F
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# 1 input image channel, 6 output channels, 3x3 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, 3)
self.conv2 = nn.Conv2d(6, 16, 3)
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
# Max pooling over a (2, 2) window
x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
# If the size is a square you can only specify a single number
x = F.max_pool2d(F.relu(self.conv2(x)), 2)
x = x.view(-1, self.num_flat_features(x))
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def num_flat_features(self, x):
size = x.size()[1:] # all dimensions except the batch dimension
num_features = 1
for s in size:
num_features *= s
return num_features
net = Net()
params = list(net.parameters())
print(params[0].size())
print(params)
input = torch.randn(1, 1, 32, 32)
out = net(input)
net.zero_grad()
out.backward(torch.randn(1, 10))
output = net(input)
target = torch.randn(10)
target = target.view(1, -1)
criterion = nn.MSELoss()
loss = criterion(output, target)
print(loss.grad_fn.next_functions[0][0]) # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0])
net.zero_grad()
print(net.conv1.bias.grad)
loss.backward()
print(net.conv1.bias.grad)
learning_rate = 0.01
for f in net.parameters():
f.data.sub_(f.grad.data * learning_rate)
import torch.optim as optim
# 创建优化器
optimizer = optim.SGD(net.parameters(), lr=0.01)
# 执行一次训练迭代过程
optimizer.zero_grad() # 梯度置零
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step() # 更新
loss
import torchvision
import torchvision.transforms as transforms
transform = transforms.Compose(
[transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 训练数据加载器
trainset = torchvision.datasets.CIFAR10(
root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(
trainset, batch_size=4, shuffle=True, num_workers=2)
# 测试数据加载器
testset = torchvision.datasets.CIFAR10(
root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(
testset, batch_size=4, shuffle=False, num_workers=2)
# 图像类别
classes = ('plane', 'car', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck')
trainloader, testloader
import matplotlib.pyplot as plt
%matplotlib inline
def imshow(img):
# 展示图像的函数
img = img / 2 + 0.5 # 反向归一化
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
# 获取随机数据
dataiter = iter(trainloader)
images, labels = next(dataiter)
# 展示图像
imshow(torchvision.utils.make_grid(images))
# 显示图像标签
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
import torch.nn as nn
import torch.nn.functional as F
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
net = Net()
net
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
optimizer
for epoch in range(100): # 迭代一次
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# 获取输入
inputs, labels = data
# 梯度置 0
optimizer.zero_grad()
# 正向传播,反向传播,优化
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# 打印状态信息
running_loss += loss.item()
if i % 200 == 199: # 每 200 批次打印一次
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 200))
running_loss = 0.0
print('Finished Training.')
dataiter = iter(testloader)
images, labels = next(dataiter)
# 显示图片
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
outputs = net(images)
outputs
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, 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))
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(4):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1
for i in range(10):
print('Accuracy of %5s : %2d%%' %
(classes[i], 100 * class_correct[i] / class_total[i]))