Implement transformation for TensorFlow 2 Map Function (aka tf.map_fn) #6836
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
Signed-off-by: Roman Kazantsev <[email protected]>
Signed-off-by: Roman Kazantsev <[email protected]>
Signed-off-by: Roman Kazantsev <[email protected]>
Signed-off-by: Roman Kazantsev <[email protected]>
There was a problem hiding this comment.
There are a number of minor comments, but in general looks good. However, I would really want to see a new layer test covering the added functionality:
- A test case where a model has one input which is consumed with the TF
Whileoperation which produces 2 outputs. - A test case where a model has two inputs which are consumed with the TF
Whileoperation which produces 2 outputs.
If one of these test cases is already covered with the existing Keras RNN-like tests that is fine. But the case which was not previously supported should be added to the pre-commit layer tests.
Signed-off-by: Roman Kazantsev <[email protected]>
Signed-off-by: Roman Kazantsev <[email protected]>
Thanks for your point. I will add it. |
lazarevevgeny
approved these changes
Jul 29, 2021
iimironov
approved these changes
Jul 29, 2021
pavel-esir
approved these changes
Jul 29, 2021
rnugmanx
pushed a commit
to rnugmanx/openvino
that referenced
this pull request
Aug 26, 2021
openvinotoolkit#6836) * Implement transformation for TensorFlow 2 Map Function primitive Signed-off-by: Roman Kazantsev <[email protected]> * Add a description for get_external_node_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Correct a name for get_external_nodes_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Fix a description for get_external_nodes_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Add logging and fix indentation Signed-off-by: Roman Kazantsev <[email protected]> * Use skip_nodes_by_condition to by-pass StopGradient nodes for tf.map_fn Signed-off-by: Roman Kazantsev <[email protected]>
andrei-cv
pushed a commit
to andrei-cv/openvino
that referenced
this pull request
Aug 30, 2021
openvinotoolkit#6836) * Implement transformation for TensorFlow 2 Map Function primitive Signed-off-by: Roman Kazantsev <[email protected]> * Add a description for get_external_node_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Correct a name for get_external_nodes_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Fix a description for get_external_nodes_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Add logging and fix indentation Signed-off-by: Roman Kazantsev <[email protected]> * Use skip_nodes_by_condition to by-pass StopGradient nodes for tf.map_fn Signed-off-by: Roman Kazantsev <[email protected]>
akuporos
pushed a commit
to akuporos/openvino
that referenced
this pull request
Sep 29, 2021
openvinotoolkit#6836) * Implement transformation for TensorFlow 2 Map Function primitive Signed-off-by: Roman Kazantsev <[email protected]> * Add a description for get_external_node_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Correct a name for get_external_nodes_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Fix a description for get_external_nodes_by_internal_id function Signed-off-by: Roman Kazantsev <[email protected]> * Add logging and fix indentation Signed-off-by: Roman Kazantsev <[email protected]> * Use skip_nodes_by_condition to by-pass StopGradient nodes for tf.map_fn Signed-off-by: Roman Kazantsev <[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.
Root cause analysis: In several TF2 OD models (MobileNet SSD V2, CenterNet) we have a preprocessor block based on tf.map_fn primitive that slices multiple inputs, transform them, and concatenate multiple intermediate outputs at each iteration of While Loop. Currently, the MO tool does not support such block.
Solution: Extend existing transformations for TF2 Keras RNN operations that are particular case of tf.map_fn when it has just one sliced input and one concatenated output. The proposed extension detects sub-graphs (from the main-graph and body-graph) for slicing and concatenation and utilizes
axisattribute of Loop operation for such operations.Ticket: 47280
Code:
Validation:
Documentation: