pytorch学习笔记

pytorch笔记（一）——— 之GuitarYang的第一篇博客

一、准备数据

构建图片数据的两种方法:

第一种是使用 torchvision中的datasets.ImageFolder来读取图片然后用 DataLoader来并行加载。

第二种是通过继承 torch.utils.data.Dataset 实现用户自定义读取逻辑然后用 DataLoader来并行加载。

其中第二种方法是读取用户自定义数据集的通用方法，既可以读取图片数据集，也可以读取文本数据集。

第一种方法如下：

import torch 
from torch import nn
from torch.utils.data import Dataset,DataLoader
from torchvision import transforms,datasets 
```

```python
transform_train = transforms.Compose(
    [transforms.ToTensor()])
transform_valid = transforms.Compose(
    [transforms.ToTensor()])

二、定义模型

使用Pytorch通常有三种方式构建模型：使用nn.Sequential按层顺序构建模型，继承nn.Module基类构建自定义模型，继承nn.Module基类构建模型并辅助应用模型容器进行封装。

此处选择使用最简单的nn.Sequential，按层顺序模型。

#1.
def create_net():
    net = nn.Sequential()
    net.add_module("linear1",nn.Linear(15,20))
    net.add_module("relu1",nn.ReLU())
    net.add_module("linear2",nn.Linear(20,15))
    net.add_module("relu2",nn.ReLU())
    net.add_module("linear3",nn.Linear(15,1))
    net.add_module("sigmoid",nn.Sigmoid())
    return net
    
net = create_net()
print(net)

#2. 
class Net(nn.Module):
    
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)
        self.pool = nn.MaxPool2d(kernel_size = 2,stride = 2)
        self.conv2 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)
        self.dropout = nn.Dropout2d(p = 0.1)
        self.adaptive_pool = nn.AdaptiveMaxPool2d((1,1))
        self.flatten = nn.Flatten()
        self.linear1 = nn.Linear(64,32)
        self.relu = nn.ReLU()
        self.linear2 = nn.Linear(32,1)
        self.sigmoid = nn.Sigmoid()
        
    def forward(self,x):
        x = self.conv1(x)
        x = self.pool(x)
        x = self.conv2(x)
        x = self.pool(x)
        x = self.dropout(x)
        x = self.adaptive_pool(x)
        x = self.flatten(x)
        x = self.linear1(x)
        x = self.relu(x)
        x = self.linear2(x)
        y = self.sigmoid(x)
        return y
        
net = Net()
print(net)

#3. 
torch.random.seed()
import torch
from torch import nn 

class Net(nn.Module):
    
    def __init__(self):
        super(Net, self).__init__()
#设置padding_idx参数后将在训练过程中将填充的token始终赋值为0向量
        self.embedding = nn.Embedding(num_embeddings = MAX_WORDS,embedding_dim = 3,padding_idx = 1)
        self.conv = nn.Sequential()
        self.conv.add_module("conv_1",nn.Conv1d(in_channels = 3,out_channels = 16,kernel_size = 5))
        self.conv.add_module("pool_1",nn.MaxPool1d(kernel_size = 2))
        self.conv.add_module("relu_1",nn.ReLU())
        self.conv.add_module("conv_2",nn.Conv1d(in_channels = 16,out_channels = 128,kernel_size = 2))
        self.conv.add_module("pool_2",nn.MaxPool1d(kernel_size = 2))
        self.conv.add_module("relu_2",nn.ReLU())
        
        self.dense = nn.Sequential()
        self.dense.add_module("flatten",nn.Flatten())
        self.dense.add_module("linear",nn.Linear(6144,1))
        self.dense.add_module("sigmoid",nn.Sigmoid())
        
    def forward(self,x):
        x = self.embedding(x).transpose(1,2)
        x = self.conv(x)
        y = self.dense(x)
        return y
        

net = Net()
print(net)

三.训练模型

Pytorch通常需要用户编写自定义训练循环，训练循环的代码风格因人而异。

有3类典型的训练循环代码风格：脚本形式训练循环，函数形式训练循环，类形式训练循环。

1.脚本形式:

# 1，训练循环-------------------------------------------------
    net.train()
    loss_sum = 0.0
    metric_sum = 0.0
    step = 1
    
    for step, (features,labels) in enumerate(dl_train, 1):
    
        # 梯度清零
        optimizer.zero_grad()

        # 正向传播求损失
        predictions = net(features)
        loss = loss_func(predictions,labels)
        metric = metric_func(predictions,labels)
        
        # 反向传播求梯度
        loss.backward()
        optimizer.step()

        # 打印batch级别日志
        loss_sum += loss.item()
        metric_sum += metric.item()
        if step%log_step_freq == 0:   
            print(("[step = %d] loss: %.3f, "+metric_name+": %.3f") %
                  (step, loss_sum/step, metric_sum/step))

2、函数形式训练循环:

def train_step(model,features,labels):
    
    # 训练模式，dropout层发生作用
    model.train()
    
    # 梯度清零
    model.optimizer.zero_grad()
    
    # 正向传播求损失
    predictions = model(features)
    loss = model.loss_func(predictions,labels)
    metric = model.metric_func(predictions,labels)

    # 反向传播求梯度
    loss.backward()
    model.optimizer.step()

    return loss.item(),metric.item()

def valid_step(model,features,labels):
    
    # 预测模式，dropout层不发生作用
    model.eval()
    # 关闭梯度计算
    with torch.no_grad():
        predictions = model(features)
        loss = model.loss_func(predictions,labels)
        metric = model.metric_func(predictions,labels)
    
    return loss.item(), metric.item()

3.类形式的训练循环

import pytorch_lightning as pl 
from torchkeras import LightModel 

class Model(LightModel):
    
    #loss,and optional metrics
    def shared_step(self,batch)->dict:
        x, y = batch
        prediction = self(x)
        loss = nn.BCELoss()(prediction,y)
        preds = torch.where(prediction>0.5,torch.ones_like(prediction),torch.zeros_like(prediction))
        acc = pl.metrics.functional.accuracy(preds, y)
        dic = {"loss":loss,"accuracy":acc} 
        return dic
    
    #optimizer,and optional lr_scheduler
    def configure_optimizers(self):
        optimizer= torch.optim.Adagrad(self.parameters(),lr = 0.02)
        return optimizer

四、评估模型

此处省略

五、使用模型

此处省略

六、保存模型

model = models.vgg16(pretrained=True)
torch.save(model.state_dict(), 'model_weights.pth')

以上就是我的第一篇博客，入园三年第一次写博客，还望和大佬多多学习！