thermometer

torchhd.thermometer(num_vectors: int, dimensions: int, vsa: Literal['BSC', 'MAP', 'HRR', 'FHRR', 'BSBC', 'VTB', 'MCR', 'CGR'] = 'MAP', *, requires_grad=False, **kwargs) → VSATensor[source]

Creates a thermometer code for given dimensionality.

Implements similarity-preserving hypervectors as described in Sparse Binary Distributed Encoding of Scalars.

Parameters:

num_vectors (int) – the number of hypervectors to generate.
dimensions (int) – the dimensionality of the hypervectors.
vsa – (VSAOptions, optional): specifies the hypervector type to be instantiated. Default: "MAP".
dtype (torch.dtype, optional) – the desired data type of returned tensor. Default: if None depends on VSATensor.
device (torch.device, optional) – the desired device of returned tensor. Default: if None, uses the current device for the default tensor type (see torch.set_default_tensor_type()). device will be the CPU for CPU tensor types and the current CUDA device for CUDA tensor types.
requires_grad (bool, optional) – If autograd should record operations on the returned tensor. Default: False.

Examples:

>>> torchhd.thermometer(7, 6, "BSC")
tensor([[False, False, False, False, False, False],
        [ True, False, False, False, False, False],
        [ True,  True, False, False, False, False],
        [ True,  True,  True, False, False, False],
        [ True,  True,  True,  True, False, False],
        [ True,  True,  True,  True,  True, False],
        [ True,  True,  True,  True,  True,  True]])

>>> torchhd.thermometer(4, 6, "MAP")
tensor([[-1., -1., -1., -1., -1., -1.],
        [ 1.,  1., -1., -1., -1., -1.],
        [ 1.,  1.,  1.,  1., -1., -1.],
        [ 1.,  1.,  1.,  1.,  1.,  1.]])

>>> torchhd.thermometer(6, 6, "FHRR")
tensor([[-1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j],
        [ 1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j],
        [ 1.+0.j,  1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j],
        [ 1.+0.j,  1.+0.j,  1.+0.j, -1.+0.j, -1.+0.j, -1.+0.j],
        [ 1.+0.j,  1.+0.j,  1.+0.j,  1.+0.j, -1.+0.j, -1.+0.j],
        [ 1.+0.j,  1.+0.j,  1.+0.j,  1.+0.j,  1.+0.j, -1.+-0.j]])