【PyTorch】Pytorch入门教程三

前面介绍了PyTorch的基本概念，接下来就直接撸代码。

代码地址：https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/01-basics/pytorch_basics/main.py#L63

Basic autograd example 1

import torch 
import torchvision
import torch.nn as nn
import numpy as np
import torch.utils.data as data
import torchvision.transforms as transforms
import torchvision.datasets as dsets
from torch.autograd import Variable

#======================= Basic autograd example 1 =======================#
# Create tensors.
x = Variable(torch.Tensor([1]), requires_grad=True)
w = Variable(torch.Tensor([2]), requires_grad=True)
b = Variable(torch.Tensor([3]), requires_grad=True)

# Build a computational graph.
y = w * x + b    # y = 2 * x + 3

# Compute gradients.
y.backward()

# Print out the gradients.
print(x.grad)    # x.grad = 2 
print(w.grad)    # w.grad = 1 
print(b.grad)    # b.grad = 1 

Basic autograd example 2

上面这段代码很简单，下面看一个复杂点的。

#======================== Basic autograd example 2 =======================#
# Create tensors.
x = Variable(torch.randn(5, 3))
y = Variable(torch.randn(5, 2))

# Build a linear layer.
linear = nn.Linear(3, 2)
print ('w: ', linear.weight)
print ('b: ', linear.bias)

# Build Loss.
criterion = nn.MSELoss()

# Forward propagation.
pred = linear(x)

# Compute loss.
loss = criterion(pred, y)
print('loss: ', loss.data[0])

# Backpropagation.
loss.backward()

# Print out the gradients.
print ('dL/dw: ', linear.weight.grad) 
print ('dL/db: ', linear.bias.grad)

# Build Optimizer.
optimizer = torch.opti