Difference between ‘register_buffer’ and ‘register_parameter’ of PyTorch Module.

参考链接：Difference between ‘register_buffer’ and ‘register_parameter’ of PyTorch Module.

nn.Parameter(torch.randn(1))

1. nn.Parameter is a subclass of torch.Tensor. Parameter class “doesn’t add any functionality other than automatically calling requires_grad.
2. Model parameters are learned and updated using SGD during the training process.
3. Parameters may be accessed through the model.parameters() method on the Module class.

register_buffer(‘buffer_name’, torch.randn(1))

1. If you have parameters in your model, that should be saved and restored in the state_dict, but not trained by the optimizer, you should register them as buffers. Buffers won’t be returned in model.parameters(), so that the o