CMSIS-NN: Add int4 kernel support to conv2d, depthwise and fully connected #2314
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
…ected Change-Id: I9a5775b709d6dc073c5ee045a884d34896bc4205
rascani
approved these changes
Nov 14, 2023
| @@ -168,6 +159,104 @@ TfLiteStatus Prepare(TfLiteContext* context, TfLiteNode* node) { | |||
| return kTfLiteOk; | |||
| } | |||
|
|
|||
| TfLiteStatus EvalQuantizedPerChannelInt4( | |||
There was a problem hiding this comment.
This function shares most of its contents with EvalQuantizedPerChannel. You may want to consider refactoring so all the structure init is shared code, with just the arm_convolve_wrapper call being different. We have other kernels where we've done this with templates, but you could also do this with init function(s) for the various param structs.
There was a problem hiding this comment.
Thanks for the comment, that's a good point. We shall do this.
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Outdated suggestions cannot be applied.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.
BUG=CMSIS-NN has support for int4 packed weights, hence updating "glue" in TFLM
Co-authored-by: Adrian Lundell [email protected], Ryan O'Shea [email protected] and Måns Nilsson [email protected]