Add tensorflow-lite recipe #1319
Draft
Conversation
This file contains hidden or 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
Tensorflow-lite needs an extremely specific flatbuffers release, 2.20 needs 24.3.25. Lock the version to that. Signed-off-by: Koen Kooi <koen.kooi@oss.qualcomm.com>
This is a combination of the 2.16.x IMSDK and 2.19.x Windriver recipes. The recipe should not be in a BSP layer, but it's the least bad place, for now. Signed-off-by: Koen Kooi <koen.kooi@oss.qualcomm.com>
koenkooi
requested review from
lumag,
ndechesne,
ricardosalveti,
sbanerjee-quic and
vkraleti
as code owners
Contributor
|
There is already meta-tensorflow. The commit message should at least explain, why we write our own recipes. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This recipe needs a better place, but, for now, put it in meta-qcom.
Tflite supports 2 buildsystems: bazel and cmake, the IMSDK recipes use cmake but only support up to 2.16.x and the Windriver recipes use bazel, but only support up to 2.19.x. Tflite 2.20 needs a more recent bazel version, which in turns needs a more recent JDK. Neither the meta-java recipes nor the meta-aws prebuilts work, so we're stuck with cmake.
Since cmake is in OE-core and we don't care about the non-lite tensorflow, the only dependency left is a specific flatbuffers release.
This was only build tested during the San Diego sprint.