graphorge.gnn_base_model.train.training.get_pytorch_optimizer

get_pytorch_optimizer(algorithm, params, **kwargs)

Get PyTorch optimizer.

Parameters:

• algorithm ({'adam',}) –

  Optimization algorithm:

  ’adam’ : Adam (torch.optim.Adam)

• params (list) – List of parameters (torch.Tensors) to optimize or list of dicts defining parameter groups.

• **kwargs – Arguments of torch.optim.Optimizer initializer.

Returns:

optimizer – PyTorch optimizer.

Return type:

torch.optim.Optimizer