机器学习

• • GPU加速训练
  • Dropout缓解过拟合
  • 批标准化

1. 对数据集进行更改
2. 对模型进行更改

两种方法：
1. .cuda()

2. device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
   .to(device)

net_dropped = torch.nn.Sequential(
    torch.nn.Linear(1, N_HIDDEN),
    torch.nn.Dropout(0.5),  # drop 50% of the neuron
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, N_HIDDEN),
    torch.nn.Dropout(0.5),  # drop 50% of the neuron
    torch.nn.ReLU(),
    torch.nn.Linear(N_HIDDEN, 1),
)

1. nn.BatchNorm1d(num_features)
2. nn.BatchNorm2d(num_features)
3. nn.BatchNorm3d(num_features)