1、自定义MyData类，继承Dataset:
重写3个函数：__init__、__getitem__、__len__
class MyData(Dataset):
#x是Feature,y是对应的结果
#初始化要把x和y转成float类型
def __init__(self,x,y=None):
if y is None:
self.y=y
else:
self.y=torch.FloatTensor(y)
self.x=torch.FloatTensor(x)
def __getitem__(self,idx):#返回x和y的值
if self.y is None:
return self.x[idx]
else:
return self.x[idx],self.y[idx]
def __len__(self):
#返回x的长度（个数）
return len(self.x)
2、从csv文件读取数据，每列表示不同的特征
train_data,test_data=pd.read_csv(r'HW01/covid.train.csv').values,pd.read_csv(r'HW01/covid.test.csv').values
3、使用DataLoder类打包MyData
train_dataset,valid_dataset,test_dataset=MyCovidData(x_train,y_train),MyCovidData(x_valid,y_valid),MyCovidData(x_test) #用DataLoader打包MyData，设置batch train_loader=DataLoader(train_dataset,batch_size=config['batch_size'],shuffle=True,pin_memory=True) valid_loader=DataLoader(valid_dataset,batch_size=config['batch_size'],shuffle=True,pin_memory=True) test_loader=DataLoader(test_dataset,batch_size=config['batch_size'],shuffle=False,pin_memory=True)
4、定义神经网络模型
class My_Model(nn.Module):
def __init__(self,input_dim):
super(My_Model,self).__init__()
self.layers=nn.Sequential(
nn.Linear(input_dim,16),
nn.ReLU(),
nn.Linear(16,8),
nn.ReLU(),
nn.Linear(8,4),
nn.ReLU(),
nn.Linear(4,1)
)
def forward(self,x):
x=self.layers(x)
x=x.squeeze(1)
return x
5、开始训练
def trainer(train_loader, valid_loader, model, config, device):
criterion = nn.MSELoss(reduction='mean') # Define your loss function, do not modify this.
# Define your optimization algorithm.
# TODO: Please check https://pytorch.org/docs/stable/optim.html to get more available algorithms.
# TODO: L2 regularization (optimizer(weight decay...) or implement by your self).
optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.9)
writer = SummaryWriter() # Writer of tensoboard.
if not os.path.isdir('./models'):
os.mkdir('./models') # Create directory of saving models.
n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0
for epoch in range(n_epochs):
model.train() # Set your model to train mode.
loss_record = []
# tqdm is a package to visualize your training progress.
train_pbar = tqdm(train_loader, position=0, leave=True)
for x, y in train_pbar:
optimizer.zero_grad() # Set gradient to zero.
x, y = x.to(device), y.to(device) # Move your data to device.
pred = model(x)
loss = criterion(pred, y)
loss.backward() # Compute gradient(backpropagation).
optimizer.step() # Update parameters.
step += 1
loss_record.append(loss.detach().item())
# Display current epoch number and loss on tqdm progress bar.
train_pbar.set_description(f'Epoch [{epoch+1}/{n_epochs}]')
train_pbar.set_postfix({'loss': loss.detach().item()})
mean_train_loss = sum(loss_record)/len(loss_record)
writer.add_scalar('Loss/train', mean_train_loss, step)
model.eval() # Set your model to evaluation mode.
loss_record = []
for x, y in valid_loader:
x, y = x.to(device), y.to(device)
with torch.no_grad():
pred = model(x)
loss = criterion(pred, y)
loss_record.append(loss.item())
mean_valid_loss = sum(loss_record)/len(loss_record)
print(f'Epoch [{epoch+1}/{n_epochs}]: Train loss: {mean_train_loss:.4f}, Valid loss: {mean_valid_loss:.4f}')
writer.add_scalar('Loss/valid', mean_valid_loss, step)
if mean_valid_loss < best_loss:
best_loss = mean_valid_loss
torch.save(model.state_dict(), config['save_path']) # Save your best model
print('Saving model with loss {:.3f}...'.format(best_loss))
early_stop_count = 0
else:
early_stop_count += 1
if early_stop_count >= config['early_stop']:
print('nModel is not improving, so we halt the training session.')
return
6、保存模型
torch.save(model.state_dict(), config['save_path'])
7、重新加载模型并预测
model=My_Model(input_dim=x_train.shape[1]).to(device)
model.load_state_dict(torch.load(config['save_path']))
#直接model(参数)即可得出预测结果
for x in tqdm(test_loader):
x = x.to(device)
with torch.no_grad():
pred = model(x)
