张量
from __future__ import print_function
import torch
x = torch.empty(5, 3)
print(x)
tensor([[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.]])
x = torch.rand(5, 3)
print(x)
tensor([[0.9009, 0.7387, 0.1229],
[0.1673, 0.8125, 0.8828],
[0.3425, 0.0978, 0.9591],
[0.4853, 0.2610, 0.1937],
[0.1460, 0.8068, 0.9388]])
x = torch.zeros(5, 3, dtype=torch.long)
print(x)
tensor([[0, 0, 0],
[0, 0, 0],
[0, 0, 0],
[0, 0, 0],
[0, 0, 0]])
x = torch.tensor([5.5, 3])
print(x)
tensor([5.5000, 3.0000])
x = x.new_ones(5, 3, dtype=torch.double) # new_* methods take in sizes
print(x)
x = torch.randn_like(x, dtype=torch.float) # override dtype!
print(x) # result has the same size
tensor([[1., 1., 1.],
[1., 1., 1.],
[1., 1., 1.],
[1., 1., 1.],
[1., 1., 1.]], dtype=torch.float64)
tensor([[-0.9599, -0.7486, -0.0417],
[ 2.2920, 1.0358, 0.9876],
[ 0.5569, -1.9474, -2.2035],
[ 1.2106, -0.5178, 1.4441],
[ 0.3283, -1.8450, -1.4182]])
y = torch.rand(5, 3)
print(x + y)
# Addition: providing an output tensor as argument
result = torch.empty(5, 3)
torch.add(x, y, out=result)
print(result)
# Addition: in-place
# adds x to y
y.add_(x)
print(y)
# Resizing: If you want to resize/reshape tensor, you can use torch.view:
x = torch.randn(4, 4)
y = x.view(16)
z = x.view(-1, 8) # the size -1 is inferred from other dimensions
print(x.size(), y.size(), z.size())
torch.Size([4, 4]) torch.Size([16]) torch.Size([2, 8])
# If you have a one element tensor, use .item() to get the value as a Python number
x = torch.randn(1)
print(x)
print(x.item())
tensor([-1.3421])
-1.3421080112457275
# Converting a Torch Tensor to a NumPy Array
a = torch.ones(5)
print(a)
b = a.numpy()
print(b)
# Converting NumPy Array to Torch Tensor
import numpy as np
a = np.ones(5)
b = torch.from_numpy(a)
np.add(a, 1, out=a)
print(a)
print(b)
# Tensors can be moved onto any device using the .to method.
# let us run this cell only if CUDA is available
# We will use ``torch.device`` objects to move tensors in and out of GPU
if torch.cuda.is_available():
device = torch.device("cuda") # a CUDA device object
y = torch.ones_like(x, device=device) # directly create a tensor on GPU
x = x.to(device) # or just use strings ``.to("cuda")``
z = x + y
print(z)
print(z.to("cpu", torch.double)) # ``.to`` can also change dtype together!
自动微分
torch.Tensor 是包的核心类。如果将其属性 .requires_grad 设置为 True,则会开始跟踪针对 tensor 的所有操作。完成计算后,您可以调用 .backward() 来自动计算所有梯度。该张量的梯度将累积到 .grad 属性中。
要停止 tensor 历史记录的跟踪,您可以调用 .detach(),它将其与计算历史记录分离,并防止将来的计算被跟踪。
要停止跟踪历史记录(和使用内存),您还可以将代码块使用 with torch.no_grad(): 包装起来。在评估模型时,这是特别有用,因为模型在训练阶段具有 requires_grad = True 的可训练参数有利于调参,但在评估阶段我们不需要梯度。
import torch
x = torch.ones(2, 2, requires_grad=True) # 创建一个张量,设置requires_grad=True 来跟踪与它相关的计算
y = x + 2
z = y * y * 3
out = z.mean()
out.backward() # 后向传播
print(x.grad) # tensor([[4.5000, 4.5000],
# [4.5000, 4.5000]])
神经网络
神经网络通过torch.nn包来构建。
一个典型的神经网络训练过程包括以下几点:
- 定义一个包含可训练参数的神经网络
- 迭代整个输入
- 通过神经网络处理输入
- 计算损失(loss)
- 反向传播梯度到神经网络的参数
- 更新网络的参数,典型的用一个简单的更新方法:weight = weight - learning_rate *gradient
import torch
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, 5x5 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 5 * 5, 120)
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()
print(net)
Net(
(conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
(conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
(fc1): Linear(in_features=400, out_features=120, bias=True)
(fc2): Linear(in_features=120, out_features=84, bias=True)
(fc3): Linear(in_features=84, out_features=10, bias=True)
)
一个模型可训练的参数可以通过调用 net.parameters() 返回:
params = list(net.parameters())
print(len(params))
print(params[0].size()) # conv1's .weight
输出:
10
torch.Size([6, 1, 5, 5])
让我们尝试随机生成一个 32x32 的输入。注意:期望的输入维度是 32x32 。为了使用这个网络在 MNIST 数据及上,你需要把数据集中的图片维度修改为 32x32。
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
tensor([[-0.0233, 0.0159, -0.0249, 0.1413, 0.0663, 0.0297, -0.0940, -0.0135,
0.1003, -0.0559]], grad_fn=<AddmmBackward>)
把所有参数梯度缓存器置零,用随机的梯度来反向传播
net.zero_grad()
out.backward(torch.randn(1, 10))
一个简单的损失函数就是 nn.MSELoss
output = net(input)
target = torch.randn(10) # a dummy target, for example
target = target.view(1, -1) # make it the same shape as output
criterion = nn.MSELoss()
loss = criterion(output, target)
print(loss)