pytorch保存模型参数并用于预测（回归模型）

太过爱你忘了你带给我的痛 2023-02-18 08:27 36阅读 0赞

数据介绍：用’name’, ‘regDate’, ‘model’, ‘brand’, ‘bodyType’, ‘fuelType’, ‘gearbox’, ‘power’， ‘kilometer’, ‘regionCode’, ‘seller’, ‘creatDate’这12个指标预测’price’  
数据集划分成了X\_train,y\_train 和 X\_test,y\_test  
我用自己定义的Dataset，作用就是把X,y向量化了而已，然后用torch.utils.data中的DataLoader导入的train\_dataloader和test\_dataloader  
打印我的train\_dataloader看下  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2t1bkFVR1VTVA_size_16_color_FFFFFF_t_70]  
这里面包含两个tensor，一个是X\_train生成的，一个是y\_train生成的  
下面开始正题  
定义网络结构：

class Net(torch.nn.Module):
        def __init__(self, n_feature, n_hidden, n_output):
            super(Net, self).__init__()
            self.hidden = torch.nn.Linear(n_feature, n_hidden)
            self.output = torch.nn.Linear(n_hidden, n_output)
    
        def forward(self, data):
            hidden = self.hidden(data)
            hidden = F.relu(hidden)
            output = self.output(hidden)
            return output

实例化model

model = Net(12, 20, 1)
    print(model)

训练过程：

NUM_EPOCHS = 10
    
    LEARNING_RATE = 0.2
    optimizer = torch.optim.SGD(model.parameters(), lr=LEARNING_RATE)
    loss_func = torch.nn.MSELoss()  # 均方差
    for epoch in range(NUM_EPOCHS):
        model.train()
        it = iter(train_dataloader)
        for i, (batch_x, batch_y) in enumerate(it):  # for each training step
            # X_train = torch.tensor(X_train, dtype=torch.float32)
            output_train = model(batch_x)
            # print(batch_x,batch_y)
            # break
            loss = loss_func(output_train, batch_y)  # 一定要prediction在前, y在后
    
            # backward
            optimizer.zero_grad()  # 梯度降零
            loss.backward()
            optimizer.step()
            if i%100 == 0:
                print('Epoch: ', epoch, 'iteration: ', i, ' loss: ', loss)
    # 保存网络参数
    torch.save(model.state_dict(), 'car.pkl')

这里要注意的是，  
1 我用dataloader生成的训练数据必须由enumerate生成迭代器来访问，访问方式为i,(x,y)  
其中i是迭代次数，x是我dataloader中的第一个tensor，y是dataloader中的第二个tensor  
2 训练模型时，要写model.train()

模型加载并用于预测  
在同一个文件中，我们要加载保存的模型，需要先重新实例化一个网络:

best_model = Net(12, 20, 1)

然后加载保存的参数：

best_model.load_state_dict(torch.load('car.pkl'))

评估：

test_loss = evaluate(best_model, test_dataloader)
    print("perplexity: ", test_loss)

其中evaluate函数为：

def evaluate(model, test_dataloader):
        model.eval()
        it = iter(test_dataloader)
        total_count = 0.
        total_loss = 0.
        with torch.no_grad():
            for i, (batch_x, batch_y) in enumerate(it):
                output_test = model(batch_x)
    
                with torch.no_grad():
                    loss = loss_func(output_test, batch_y)
                    # print(type(loss))  # <class 'torch.Tensor'>
                    # print(loss)  # tensor(41197140.)
                    total_count += np.multiply(*batch_x.size())
                    total_loss += loss.item() * np.multiply(*batch_x.size())
    
        loss = total_loss / total_count
        model.train()
        return loss

这里要注意的是：  
1 最开头要写model.eval()  
2 跳出for循环以后，要再加上model.train()，否则会报错

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2t1bkFVR1VTVA_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200616204629100.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2t1bkFVR1VTVA==,size_16,color_FFFFFF,t_70