reference/generated/tensordict.TensorDictBase.lerp

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

TensorDictBase.lerp

TensorDictBase.lerp(end: TensorCollection | Tensor, weight: TensorCollection | Tensor | float) → Self

Does a linear interpolation of two tensors start (given by self) and end based on a scalar or tensor weight.

\[\text{out}_i = \text{start}_i + \text{weight}_i \times (\text{end}_i - \text{start}_i)\]

The shapes of start and end must be broadcastable. If weight is a tensor, then the shapes of weight, start, and end must be broadcastable.

Parameters:

• end (TensorDict) – the tensordict with the ending points.

• weight (TensorDict, tensor or float) – the weight for the interpolation formula.

Every tensordict class and every tensorclass has this method. For the other methods, see Methods by task.