Repository navigation
Use the implicit simulator target and model parameters in mlops: - #28
Merged
Merged
Conversation
From the preview branch, now that CMSIS-Toolbox 2.15.0 is released: the toolbox detects the simulator target from the Arm-FVP target-set, so simulator: goes, and passes extra keys under model: through to *.cbuild-mlops.yml. The input shape (NHWC, 1x16x16x3) and the number of calibration samples move there; model_params() in create_ai_layer.py hands them to model/model.py. The exported program is unchanged (8720 bytes, same logits).
This was referenced Oct 6, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Brings the
previewbranch's MLOps feature tomain. It needed CMSIS-Toolbox 2.14.1+p88 and is supported by the released 2.15.0 (pinned in vcpkg since #27).simulator: target:goes: the toolbox finds the simulator from the Arm-FVP target-set.input-shape(NHWC,1x16x16x3, following Take the model input as NHWC #26) andcalibration-samplesmove undermlops: model:. The toolbox copies them into*.cbuild-mlops.yml, andmodel_params()increate_ai_layer.pypasses them tomodel/model.py. Any other extra key gets a warning.documentation/mlops-flow.mdupdated; the*.cbuild-mlops.ymlsample is regenerated.The rest of
preview(ExecuTorch 1.4.1, the CI gate on the toolbox version, the docs) is older thanmainand is not carried over. Once this PR is merged,previewcan be retired.Tested locally with toolbox 2.15.1:
cbuild-mlops.ymlcontains the two keys and the detected simulator, andcreate_ai_layer.pyregenerates an identical AI layer (8720 bytes, no diff inai_layer/). This PR's CI covers vcpkg 2.15.0 with AC6, GCC and CLANG.