Computes and stores the average and current value

A helper class for managing registering modules, it extends a dictionary and provides a register functions. Eg. creeting a registry:

Gradually warm-up(increasing) learning rate in optimizer. Proposed in 'Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour'. Args:

r"""Implement of large margin cosine distance: : Args: in_features: size of each input sample out_features: size of each output sa

Sampler that restricts data loading to a subset of the dataset. It is especially useful in conjunction with :class:`torch.nn.parallel.Distribu

r"""Implement of softmax with margin: Args: in_features: size of each input sample out_features: size of each output sample

docstring for ClassName

docstring for ClassName