Functions#

Summary #

function	class parent	truncated documentation
`apply_transitions`		Applies a list of transitions (permutations of two elements) on the first n integers.
`check`		Runs a couple of functions to check the module is working.
`decompose_permutation`		Decomposes a permutation into transitions.
`main`		Implements `python -m onnxcustom <command> <args>`.
`onnx_rename_weights`		Renames ONNX initialiers to make sure their name follows the alphabetical order. The model is modified inplace. …
`ort_backward`		Implements backward function. See autograd functions.
`ort_forward`		Implements forward function. See autograd functions.
`save_as_onnx`		Converts a torch model into ONNX using `torch.onnx.export()`. The function works on models with only one input. …

Classes

Methods