Create a hybrid tf-tfl lowering pipline for TOSA #52686
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
By adding the pass to lift Flex ops to TensorFlow Dialect operations it is possible to have a mixture of both TensorFlow and TensorFlow Lite dialects. Having a combined set of patterns using TOSA's shape inference frameowrk it is possible to fully lower / shape infer TFLite models with flex operations. These patterns must be included in a single pass so that shape inference can execute on both dialects. If performed separately, lack of cooperating lowerings may not result in a fully available lowering.
google-ml-butler
bot
added
awaiting review
copybara-service bot
pushed a commit
to iree-org/iree
that referenced
this pull request
Oct 27, 2021
Imported from GitHub PR tensorflow/tensorflow#52686 By adding the pass to lift Flex ops to TensorFlow Dialect operations it is possible to have a mixture of both TensorFlow and TensorFlow Lite dialects. Having a combined set of patterns using TOSA's shape inference frameowrk it is possible to fully lower / shape infer TFLite models with flex operations. These patterns must be included in a single pass so that shape inference can execute on both dialects. If performed separately, lack of cooperating lowerings may not result in a fully available lowering. Copybara import of the project: -- 14789179cc251ab5787daa5a07e41b563c900fbb by Rob Suderman <rob.suderman@gmail.com>: Create a hybrid tf-tfl lowering pipline for TOSA By adding the pass to lift Flex ops to TensorFlow Dialect operations it is possible to have a mixture of both TensorFlow and TensorFlow Lite dialects. Having a combined set of patterns using TOSA's shape inference frameowrk it is possible to fully lower / shape infer TFLite models with flex operations. These patterns must be included in a single pass so that shape inference can execute on both dialects. If performed separately, lack of cooperating lowerings may not result in a fully available lowering. PiperOrigin-RevId: 405994127
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.
By adding the pass to lift Flex ops to TensorFlow Dialect operations it is
possible to have a mixture of both TensorFlow and TensorFlow Lite dialects.
Having a combined set of patterns using TOSA's shape inference frameowrk it is
possible to fully lower / shape infer TFLite models with flex operations.
These patterns must be included in a single pass so that shape inference can
execute on both dialects. If performed separately, lack of cooperating
lowerings may not result in a fully available lowering.