-
Notifications
You must be signed in to change notification settings - Fork 35
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Remove unused packbits_arm32 #437
Merged
Merged
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
Tombana
approved these changes
Jul 22, 2020
AdamHillier
approved these changes
Jul 22, 2020
lgeiger
added a commit
that referenced
this pull request
Nov 13, 2020
* Fix link to api/converter (#413) * Improve error message when passing wrong converter arg (#414) * Improve error message when passing wrong converter arg (#414) * Replace context->ReportError calls with TF_LITE_KERNEL_LOG (#403) * Create Dependabot config file (#416) Co-authored-by: dependabot-preview[bot] <27856297+dependabot-preview[bot]@users.noreply.github.com> * Bump toolmantim/release-drafter from v5.8.0 to v5.11.0 (#417) Bumps [toolmantim/release-drafter](https://github.com/toolmantim/release-drafter) from v5.8.0 to v5.11.0. - [Release notes](https://github.com/toolmantim/release-drafter/releases) - [Commits](release-drafter/release-drafter@v5.8.0...06d4616) Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump actions/upload-artifact from v1 to v2.0.1 (#419) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from v1 to v2.0.1. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](actions/upload-artifact@v1...97b7dac) Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump actions/download-artifact from v1 to v2 (#418) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from v1 to v2. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](actions/download-artifact@v1...1de1dea) Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Upgrade TensorFlow to 2.3.0rc0 (#415) * ⬆️ [email protected] * Integrate conversion pass changes * Rename kTfLiteActRelu1 to kTfLiteActReluN1To1 See tensorflow/tensorflow@f24d25d * Remove broken non-float int8 output-transform (#422) * Bump actions/upload-artifact from v2.0.1 to 2.1.0 (#425) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from v2.0.1 to 2.1.0. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](actions/upload-artifact@v2.0.1...ebad382) Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Bump DoozyX/clang-format-lint-action from v0.6 to v0.7 (#427) Bumps [DoozyX/clang-format-lint-action](https://github.com/DoozyX/clang-format-lint-action) from v0.6 to v0.7. - [Release notes](https://github.com/DoozyX/clang-format-lint-action/releases) - [Commits](DoozyX/clang-format-lint-action@v0.6...d9291de) Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Refactor OutputTransform template types (#426) * Bump actions/setup-python from v2 to v2.1.1 (#429) Bumps [actions/setup-python](https://github.com/actions/setup-python) from v2 to v2.1.1. - [Release notes](https://github.com/actions/setup-python/releases) - [Commits](actions/setup-python@v2...0c28554) Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * Update the unittest error threshold (#430) Lately the ARM32 unittests have been failing more often with very small floating point mismatches. This commit slightly increases the tolerance. * Bump DoozyX/clang-format-lint-action from v0.7 to v0.8 (#433) Bumps [DoozyX/clang-format-lint-action](https://github.com/DoozyX/clang-format-lint-action) from v0.7 to v0.8. - [Release notes](https://github.com/DoozyX/clang-format-lint-action/releases) - [Commits](DoozyX/clang-format-lint-action@v0.7...492fc0f) Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * ⬆️ lce_register.cc (#434) * Test converter against TF 2.3 (#436) * Test converter against TF 2.3.0rc2 * ⬆️ pip dependencies on CI * Remove unused packbits_arm32 (#437) * 🔥 packbits_arm32 * Remove missing tests from arm32 test script * Fix typo in test script Co-authored-by: Koen Helwegen <[email protected]> Co-authored-by: Lukas Geiger <[email protected]> Co-authored-by: dependabot-preview[bot] <27856297+dependabot-preview[bot]@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
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.
What do these changes do?
This PR removes
packbits_arm32.cc
and the related unittests. This file contained a dummy implementation for ARM32 that was leftover from early experiments and never used in the actual kernels.How Has This Been Tested?
CI
Related issue number
This shouldn't impact #432 as it uses the canonical bitpacking implementation, but we might want to bring back an optimized bitpacking implementation for ARM32 once #432 is merged and #435 is implemented.