目录
固定的随机数种子
在大量的机器学习与深度学习实验中，如果不进行特殊设置，我们的结果将不可复现，固定的随机数种子将会解决这个问题
python
def same_seed(seed):
'''
设置随机种子(便于复现)
'''
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(seed)
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed_all(seed)
print(f'Set Seed = {seed}')定义predict功能
在自己进行完整的训练框架搭建时，对于结果的预测功能搭建，需要分离被预测对象，否则预测的对象的梯度会回传，扰乱模型backbone
python
def predict(test_loader, model, device):
model.eval() # 设置成eval模式.
preds = []
for x in tqdm(test_loader):
x = x.to(device)
with torch.no_grad():
pred = model(x)
preds.append(pred.detach().cpu())
#detach()从GPU分离tensor, cpu()将tensor从GPU转到CPU
preds = torch.cat(preds, dim=0).numpy()
# 将预测结果拼接成一个numpy矩阵
return preds拆分数据集
对于原始数据集（分类）的拆分函数
python
def train_valid_split(data_set, valid_ratio, seed):
'''
数据集拆分成训练集（training set）和 验证集（validation set）
'''
valid_set_size = int(valid_ratio * len(data_set))
train_set_size = len(data_set) - valid_set_size
train_set, valid_set = random_split(data_set, [train_set_size, valid_set_size],
generator=torch.Generator().manual_seed(seed))
return np.array(train_set), np.array(valid_set)定义trainer
python
def trainer(train_loader, valid_loader, model, config, device):
criterion = nn.MSELoss(reduction='mean') # 损失函数的定义
# 定义优化器
optimizer = torch.optim.SGD(model.parameters(), lr=config['learning_rate'], momentum=0.9)
# tensorboard 的记录器
writer = SummaryWriter()
if not os.path.isdir('./models'):
# 创建文件夹-用于存储模型
os.mkdir('./models')
n_epochs, best_loss, step, early_stop_count = config['n_epochs'], math.inf, 0, 0
for epoch in range(n_epochs):
model.train() # 训练模式
loss_record = []
# tqdm可以帮助我们显示训练的进度
train_pbar = tqdm(train_loader, position=0, leave=True)
# 设置进度条的左边 ： 显示第几个Epoch了
train_pbar.set_description(f'Epoch [{epoch+1}/{n_epochs}]')
for x, y in train_pbar:
optimizer.zero_grad() # 将梯度置0.
x, y = x.to(device), y.to(device) # 将数据一到相应的存储位置(CPU/GPU)
pred = model(x)
loss = criterion(pred, y)
loss.backward() # 反向传播 计算梯度.
optimizer.step() # 更新网络参数
step += 1
loss_record.append(loss.detach().item())
# 训练完一个batch的数据，将loss 显示在进度条的右边
train_pbar.set_postfix({'loss': loss.detach().item()})
mean_train_loss = sum(loss_record)/len(loss_record)
# 每个epoch,在tensorboard 中记录训练的损失（后面可以展示出来）
writer.add_scalar('Loss/train', mean_train_loss, step)
model.eval() # 将模型设置成 evaluation 模式.
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}')
# 每个epoch,在tensorboard 中记录验证的损失（后面可以展示出来）
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']) # 模型保存
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超参数设置
python
device = 'cuda' if torch.cuda.is_available() else 'cpu'
config = {
'seed': 5201314, # 随机种子，可以自己填写. :)
'select_all': True, # 是否选择全部的特征
'valid_ratio': 0.2, # 验证集大小(validation_size) = 训练集大小(train_size) * 验证数据占比(valid_ratio)
'n_epochs': 3000, # 数据遍历训练次数
'batch_size': 256,
'learning_rate': 1e-5,
'early_stop': 400, # 如果early_stop轮损失没有下降就停止训练.
'save_path': './models/model.ckpt' # 模型存储的位置
}数据集载入
python
# 使用Pytorch中Dataloader类按照Batch将数据集加载
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)模型训练
python
model = My_Model(input_dim=x_train.shape[1]).to(device)
# 将模型和训练数据放在相同的存储位置(CPU/GPU)
trainer(train_loader, valid_loader, model, config, device)模型测试
python
def save_pred(preds, file):
''' 将模型保存到指定位置'''
with open(file, 'w') as fp:
writer = csv.writer(fp)
writer.writerow(['id', 'tested_positive'])
for i, p in enumerate(preds):
writer.writerow([i, p])
model = My_Model(input_dim=x_train.shape[1]).to(device)
model.load_state_dict(torch.load(config['save_path']))
preds = predict(test_loader, model, device)
save_pred(preds, 'pred.csv')