To keep track of the stochastic computation graph, Storchastic returns wrapped
torch.Tensor that are subclasses of
storch.Tensor. This wrapper contains information that allows Storchastic to analyse the computation graph
during inference to properly estimate gradients. Furthermore,
storch.Tensor contains plate information that allows
for automatic broadcasting with other
storch.Tensor objects with different plate information.
- class storch.tensor.IndependentTensor(tensor: torch.Tensor, parents: [Tensor], plates: [Plate], tensor_name: str, plate_name: str, weight: Optional[storch.Tensor])¶
Used to denote independencies on a Tensor. This could for example be the minibatch dimension. The first dimension of the input tensor is taken to be independent and added as a batch dimension to the storch system.
- stochastic() bool ¶
True if this is a stochastic node in the stochastic computation graph, False otherwise.
- Return type