Allow parsing input tensors from torch ScriptModules
#57
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
EthanMarx
added a commit
that referenced
this pull request
Oct 3, 2024
* add ability to parse inputs from script module * update torch dep to ^2.0 for consistency with ml4gw * add onnx dep * remove both tests * remove both tests
EthanMarx
added a commit
that referenced
this pull request
Oct 3, 2024
* Allow parsing input tensors from torch `ScriptModules` (#57) * add ability to parse inputs from script module * update torch dep to ^2.0 for consistency with ml4gw * add onnx dep * remove both tests * remove both tests * Batched state updates (#59) * allow for batched state updates * update poetry lock * restrict tf version * revert whitespaces * Allow python 3.12 and explicitly list PyPI as a source for future compatibility * Add python 3.12 to unit tests * Add py312 to tox file * Missed one * Attempt to update tensorflow * Change tf specification * Force usage of keras 2 * Fix formatting * Remove py38 support and install tf-keras * More intelligent and flexible input and output tensor naming for `TorchScript` Exporter (#62) * support direct torchscript export from ScriptModule * add tests of new naming behavior * guard torch import * add jit module to handles for onnx and torchscript exporters * add script module test to exporter utils * bump to version 0.2.0 (#64) --------- Co-authored-by: William Benoit <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
When converting from torch model to tensorrt, if input is a TorchScript model, it is not possible to directly infer model parameters from forward method via inspect library.
Instead, infer parameters directly from model graph.
Updates
torchversion to^2.0for consistency withml4gwreopened version of #49