clausal-torch

PyTorch predicates for Clausal Prolog.

Wraps PyTorch as Clausal Prolog predicates: tensors (creation, math, shape operations, comparisons, conversions), nn module structure and gradient utilities, nn.functional, probability distributions and datasets.

Install

pip install clausal-torch

torch is pulled in as a dependency. Requires Python 3.13 or later.

Use

Import the predicates into a seam (.seam) module, as the package's own tests do. A Clausal Prolog (.clausal) module reaches Python only through the seam: put the imports in a .seam module and list it under [tool.clausal] python_bridges in your project's pyproject.toml (see Importing Prolog).

This test, from tests/fixtures/torch_comparison_tests.seam, shows the shape of a call:

-import_from(torch, [tensor, eq, tensor_list])

test("eq element-wise") <- (
    tensor([1.0, 2.0, 3.0], A),
    tensor([1.0, 0.0, 3.0], B),
    eq(A, B, C),
    tensor_list(C, [True, False, True])
)

Documentation

• torch — PyTorch Tensor Operations
• torch_data — Datasets
• torch_distributions — Probability Distributions
• torch_functional — nn.functional
• torch_nn — Module Structure, Registries, and Gradient Utilities

License

MIT