pytorch（视频课笔记）

回归

import torch
import torch.nn as nn
import torch.nn.functional as F

x=torch.unsqueeze(torch.linspace(-1,1,100),dim=1)#在dim维度插入一维
y=x.pow(2)+0.2*torch.rand(x.size())

class Net(nn.Module):
    def __init__(self,n_features,n_hidden,n_output):
        super(Net, self).__init__()
        self.hidden=torch.nn.Linear(n_features,n_hidden)#隐藏层
        self.predict = torch.nn.Linear(n_hidden, n_output)  # 隐藏层

    def forward(self,x):
        x=F.relu(self.hidden(x))
        x=self.predict(x)
        return x

net=Net(1,10,1)
print(net)

optimizer=torch.optim.SGD(net.parameters(),lr=0.5)
loss_func=torch.nn.MSELoss()#均方差

for t in range(100):#100步
    prediction=net(x)

    loss=loss_func(prediction,y)#真实值在后

    optimizer.zero_grad()#梯度降为0
    loss.backward()#反向传递过程
    optimizer.step()#优化

分类

import torch
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
from torch.autograd import Variable

# 假数据
n_data = torch.ones(100, 2)  # 数据的基本形态
x0 = torch.normal(2 * n_data, 1)  # 类型0 x data (tensor), shape=(100, 2)
y0 = torch.zeros(100)  # 类型0 y data (tensor), shape=(100, )
x1 = torch.normal(-2 * n_data, 1)  # 类型1 x data (tensor), shape=(100, 1)
y1 = torch.ones(100)  # 类型1 y data (tensor), shape=(100, )

# 注意 x, y 数据的数据形式是一定要像下面一样 (torch.cat 是在合并数据)
x = torch.cat((x0, x1), 0).type(torch.FloatTensor)  # FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)  # LongTensor = 64-bit integer

x, y = Variable(x), Variable(y)


class Net(nn.Module):
    def __init__(self, n_features, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_features, n_hidden)  # 隐藏层
        self.predict = torch.nn.Linear(n_hidden, n_output)  # 隐藏层

    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x


net = Net(2, 10, 2)
print(net)

optimizer = torch.optim.SGD(net.parameters(), lr=0.02)
loss_func = torch.nn.CrossEntropyLoss()  # 均方差

for t in range(100):  # 100步
    out = net(x)

    loss = loss_func(out, y)  # 真实值在后

    optimizer.zero_grad()  # 梯度降为0
    loss.backward()  # 反向传递过程
    optimizer.step()  # 优化

快速搭建

net2=torch.nn.Sequential(
    torch.nn.Linear(1, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 1)
)

保存提取

import torch
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
from torch.autograd import Variable

# 假数据
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size())  # noisy y data (tensor), shape=(100, 1)

def save():
    #save net1
    net1 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )
    optimizer=torch.optim.SDG(net1.parameters(),lr=0.5)
    loss_func=torch.nn.MSELoss()

    for t in range(100):
        prediction = net1(x)
        loss=loss_func(prediction,y)
        optimizer.ze_grad()
        loss.backward()
        optimizer.step()

    torch.save(net1,'net.pkl')#保存整个
    torch.save(net1.state_dict(),'net_params.pkl')

def restore_net():
    net2=torch.load('net.pkl')

def restore_params():
    net3=torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )
    net3.load_state_dict(torch.load('net_params.pkl'))

批处理

import torch
import torch.utils.data as Data
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
from torch.autograd import Variable

BATCH_SIZE=5

x=torch.linspace(1,10,10)
y=torch.linspace(10,1,10)

# 先转换成 torch 能识别的 Dataset
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)

# 把 dataset 放入 DataLoader
loader = Data.DataLoader(
    dataset=torch_dataset,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # mini batch size
    shuffle=True,               # 要不要打乱数据 (打乱比较好)
    num_workers=2,              # 多线程来读数据
)

for epoch in range(3):   # 训练所有!整套!数据 3 次
    for step, (batch_x, batch_y) in enumerate(loader):  # 每一步 loader 释放一小批数据用来学习
        # 假设这里就是你训练的地方...

批训练错误之got an unexpected keyword

if __name__ == '__main__':
    x = torch.linspace(1, 10, 10)
    y = torch.linspace(10, 1, 10)

    # 先转换成 torch 能识别的 Dataset
    torch_dataset = data.TensorDataset(x, y)

优化器

import torch
import torch.utils.data as Data
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
from torch.autograd import Variable

if __name__ == '__main__':
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

# fake dataset
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim=1)
y = x.pow(2) + 0.1 * torch.normal(torch.zeros(*x.size()))

torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)


class Net(nn.Module):
    def __init__(self, n_features, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_features, n_hidden)  # 隐藏层
        self.predict = torch.nn.Linear(n_hidden, n_output)  # 隐藏层

    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x


net_SGD = Net()
net_Momentum = Net()
net_RMSprop = Net()
net_Adam = Net()
nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]

opt_SGD = torch.optim.SGD(net_SGD.parameters(), lr=LR)
opt_Momentum = torch.optim.SGD(net_Momentum.parameters(), lr=LR, momentum=0.8)
opt_RMSprop = torch.optim.RMSprop(net_RMSprop.parameters(), lr=LR, alpha=0.9)
opt_Adam = torch.optim.Adam(net_Adam.parameters(), lr=LR, betas=(0.9, 0.99))
optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]

loss_func = torch.nn.MSELoss()  # 均方差
losses_his = [[], [], [], []]

for epoch in range(EPOCH):
    print(epoch)
    for step, (batch_x, batch_y) in enumerate(loader):
        b_x = Variable(batch_x)
        b_y = Variable(batch_y)
        for net, opt, l_his in zip(nets, optimizers, losses_his):
            output = net(b_x)  # get output for every net
            loss = loss_func(output, b_y)  # compute loss for every net
            opt.zero_grad()  # clear gradients for next train
            loss.backward()  # backpropagation, compute gradients
            opt.step()  # apply gradients
            l_his.append(loss.data.numpy())  # loss recoder

CNN

import torch
import torch.utils.data as Data
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
import torchvision
from torch.autograd import Variable

if __name__ == '__main__':
    EPOCH = 1  # 训练整批数据多少次, 为了节约时间, 我们只训练一次
    BATCH_SIZE = 50
    LR = 0.001  # 学习率
    DOWNLOAD_MNIST = True  # 如果你已经下载好了mnist数据就写上 False

    train_data = torchvision.datasets.MNIST(
        root='./mnist/',
        train=True,
        transform=torchvision.transforms.ToTensor(),
        download=DOWNLOAD_MNIST
    )

    train_data = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

    test_data = torchvision.datasets.MNIST(root='/4Tdisk/zhouyunfan/mnist/', train=False)  # 获取测试数据集
    test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[
             :2000] / 255.  # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
    test_y = test_data.test_labels[:2000]


    class CNN(nn.Module):
        def __init__(self):
            super(CNN, self).__init__()
            self.conv1 = nn.Sequential(
                nn.Conv2d(
                    in_channels=1,  # 层数
                    out_channels=16,  # 输出高度
                    kernel_size=5,  # 扫描区域大小
                    stride=1,  # 跳度范围
                    padding=2  # 在周围加上一圈0数据
                    # 如果想要 con2d 出来的图片长宽没有变化, padding=(kernel_size-1)/2 当 stride=1
                ),  # 卷积层：过滤器，收集信息
                nn.ReLU(),  # 神经网络
                nn.MaxPool2d(kernel_size=2),  # 池化层：筛选值
            )
            self.conv2 = nn.Sequential(
                nn.Conv2d(16, 32, 1, 2),
                nn.ReLU(),
                nn.MaxPool2d(2),
            )
            self.out = nn.Linear(32 * 7 * 7, 10)

        def forward(self, x):
            x = self.conv1(x)
            x = self.conv2(x)
            x = x.view(x.size(0), -1)
            output=self.out(x)
            return x