pytorch demo

import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import torch
import torch.optim as optim

class Net(nn.Module):#需要继承这个类
    def __init__(self):
        super(Net, self).__init__()       # 建立了两个卷积层，self.conv1, self.conv2，注意，这些层都是不包含激活函数的
        self.conv1 = nn.Conv2d(1, 6, 5)   # 1 input image channel, 6 output channels, 5x5 square convolution kernel
        self.conv2 = nn.Conv2d(6, 16, 5)  # 三个全连接层
        self.fc1 = nn.Linear(16*5*5, 120) # an affine operation: y = Wx + b
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
    def forward(self, x):                 # 注意，2D卷积层的输入data维数是 batchsize*channel*height*width
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))  # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)       # If the size is a square you can only specify a single number
        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)
# print(len(list(net.parameters())))
#
# input = Variable(torch.randn(1, 1, 32, 32))
# out = net(input)

net = Net()   # create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)

learning_rate=0.001
input_data=torch.randn(2, 1, 32, 32)
# input_data=Variable(input_data)
target=torch.FloatTensor(2, 10).random_(8)
print(target)
criterion = torch.nn.MSELoss(reduce=True, size_average=True)
# in your training loop:
for i in range(1000):
    optimizer.zero_grad()      # zero the gradient buffers，如果不归0的话，gradients会累加
    output = net(input_data)   # 这里就体现出来动态建图了，你还可以传入其他的参数来改变网络的结构

    loss = criterion(output, target)
    loss.backward()             # 得到grad，i.e.给Variable.grad赋值
    optimizer.step()            # Does the update，i.e.

print(output)

output

tensor([[1., 3., 4., 3., 5., 1., 6., 6., 6., 6.],
        [1., 2., 2., 7., 2., 4., 0., 4., 3., 6.]])

tensor([[1.0419, 3.0951, 4.0900, 3.2657, 5.1304, 1.1834, 6.0200, 6.1616, 6.1678,
         6.2592],
        [0.9804, 2.0937, 2.2189, 6.6986, 2.2809, 3.8273, 0.5658, 4.1855, 3.3320,
         6.0890]], grad_fn=<ThAddmmBackward>)

线性回归

import torch
from torch.autograd import Variable

# train data
x_data = Variable(torch.Tensor([[1.0], [2.0], [3.0]]))
y_data = Variable(torch.Tensor([[2.0], [4.0], [6.0]]))

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear = torch.nn.Linear(1, 1)
        # One in and one out
    def forward(self, x):
        y_pred = self.linear(x)
        return y_pred

    # our model
model = Model()

criterion = torch.nn.MSELoss(size_average=False)
# Defined loss function
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
# Defined optimizer
#  Training: forward, loss, backward, step
#  Training loop
for epoch in range(500):
    #  Forward pass
    y_pred = model(x_data)
    # Compute loss
    loss = criterion(y_pred, y_data)
    print(epoch, loss.data[0])
    # Zero gradients
    optimizer.zero_grad()
    # perform backward pass
    loss.backward()
    # update weights
    optimizer.step()

# After training

hour_var = Variable(torch.Tensor([[7.0]]))
print("predict (after training)", 4, model.forward(hour_var).data[0][0])

逻辑回归

import torch
from torch.autograd import Variable

x_data = Variable(torch.Tensor([[0.4], [1.0], [3.5], [4.0]]))
y_data = Variable(torch.Tensor([[0.], [0.], [1.], [1.]]))

class Model(torch.nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.linear = torch.nn.Linear(1, 1)
        # One in one out
        self.sigmoid = torch.nn.Sigmoid()

    def forward(self, x):
        y_pred = self.sigmoid(self.linear(x))
        return y_pred
        # Our model

model = Model() # Construct loss function and optimizer
criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
# Training loop
for epoch in range(80000): # Forward pass

    y_pred = model(x_data) # Compute loss
    loss = criterion(y_pred, y_data)
    if epoch % 20 == 0:
        print(epoch, loss.data[0])
        # Zero gradients
        optimizer.zero_grad() # Backward pass
        loss.backward() # update weights
        optimizer.step() # After training

hour_var = Variable(torch.Tensor([[0.5]]))
print("predict (after training)", 0.5, model.forward(hour_var).data[0][0])
hour_var = Variable(torch.Tensor([[7.0]]))
print("predict (after training)", 7.0, model.forward(hour_var).data[0][0])

备注

pytorch0.4 的tensor和variable合在一起了，所以可以直接计算，低版本的还需将tensor包装进variable才能求导。