tools#

Maths#

deeponnxcustom.tools.math_helper.apply_transitions (n, transitions)

Applies a list of transitions (permutations of two elements) on the first n integers.

deeponnxcustom.tools.math_helper.decompose_permutation (perm)

Decomposes a permutation into transitions.

ONNX#

deeponnxcustom.tools.onnx_helper.onnx_rename_weights (onx)

Renames ONNX initialiers to make sure their name follows the alphabetical order. The model is modified inplace. This function calls onnx_rename_names.

deeponnxcustom.tools.onnx_helper.save_as_onnx (model, filename, size = None, target_opset = 14, batch_size = 1, device = ‘cpu’, keep_initializers_as_inputs = False)

Converts a torch model into ONNX using torch.onnx.export(). The function works on models with only one input.