pytorch笔记

PyTorch Docs

1、torch

torch.optim

• BGD(): batch gradient descent
• SGD(): stochastic gradient descent
• MBGD(): mini-batch gradient descent
• Adam()

torch.nn

• MESLoss(): mean square error，均方误差

• NLLLoss(): Negative Log Likelihood Loss

• BCELoss(): Binary Cross Entropy Loss

  		BCELoss(x, y)
  

  $$-\frac{1}{n}\sum (y_n\times \ln x_n+(1-y_n)\times \ln (1-x_n))$$

• BCEWithLOgitsLoss

• CrossEntropyLoss():

• Linear()

• Sigmoid()

• relu()

• Module

torch.nn.functional

• cross_entropy()，交叉损失熵

torch.cuda

• is_available()

torch.utils

• save_image()

torch.utils.data

• TensorDataset
• DataLoader

2、torchvision