Fallback to TFLM processing logic for per-channel data in FullyConnected (TFMIC-52) #109
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
github-actions
bot
changed the title
vikramdattu
reviewed
Feb 7, 2025
- ESP-NN currently does not have a function for per-channel data - Using the existing method gives incorrect outputs - Fallback to TFLM implementation in such cases
ShardulNalegave
force-pushed
the
fully_connected_channelwise_fallback
branch
from
8818b4c to
d4268f0
Compare
|
I will close the PR, since the per ch optimisation is available and can be pulled in with |
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Outdated suggestions cannot be applied.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.
Description
TFLM has a separate
FullyConnectedPerChannelimplementation for per-channel data. There existing ESP-NN method used for this data and gives incorrect outputs. Therefore, ifdata.is_per_channelis true then fallback to TFLM implementation for the time being.Testing
Test ran a MobileNetV2 quantized model and compared its expected and actual outputs after this fix.
Checklist
Before submitting a Pull Request, please ensure the following: