Shortcuts

UninitializedParameter

class torch.nn.parameter.UninitializedParameter(requires_grad=True)[source]

A parameter that is not initialized.

Unitialized Parameters are a a special case of torch.nn.Parameter where the shape of the data is still unknown.

Unlikely a torch.nn.Parameter, uninitialized parameters hold no data and attempting to access some properties, like their shape, will throw a runtime error. The only operations that can be performed on a uninitialized parameter are changing its datatype, moving it to a different device and converting it to a regular torch.nn.Parameter.

materialize(shape, device=None, dtype=None)[source]

Create a Parameter with the same properties of the uninitialized one. Given a shape, it materializes a parameter in the same device and with the same dtype as the current one or the specified ones in the arguments.

Parameters
  • shape – (tuple): the shape for the materialized tensor.

  • device (torch.device) – the desired device of the parameters and buffers in this module. Optional.

  • dtype (torch.dtype) – the desired floating point type of the floating point parameters and buffers in this module. Optional.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources