Add MedImageParse3D finetune component#5053
Merged
Merged
Conversation
Adds a new commandComponent (medimageparse_3d_finetune v0.0.1) that fine-tunes the MedImageParse 3D (MIP-3D) model on volumetric medical image data via the olympus_biomed_parse_3d package.
Mirrors the medimage_parse (2D) component layout:
- components/finetune/medimage_parse_3d/{asset,spec}.yaml
- src/medimage_parse_3d_finetune/{medimageparse_3d_finetune.py,train_launcher.sh}
Pins environment acft-medimageparse-3d-finetune/versions/1, which is added by PR #5032; component build will succeed once that env PR merges.
Validated end-to-end with AML job maroon_horse_szbvr35pw1.
Test Results for assets-test0 tests 0 ✅ 0s ⏱️ Results for commit 090bd2e. ♻️ This comment has been updated with latest results. |
vizhur
approved these changes
May 19, 2026
sidkiblawi
added
the
safe to publish
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds a new
commandComponent(medimageparse_3d_finetunev0.0.1) that fine-tunes the MedImageParse 3D (MIP-3D) model on volumetric medical image data via theolympus_biomed_parse_3dpackage.Mirrors the existing 2D
medimage_parsecomponent layout exactly:assets/training/finetune_acft_image/components/finetune/medimage_parse_3d/{asset,spec}.yamlassets/training/finetune_acft_image/src/medimage_parse_3d_finetune/{medimageparse_3d_finetune.py,train_launcher.sh}Interface
pretrained_mlflow_modeluri_folderbiomedparse_v2.ckptdatauri_foldertrain.json,train/,train_mask/)configuri_fileparameters.yaml(Hydra overrides — merged in via the- parametersdefault in the wheel'sMIP3D_finetune.yaml)outuri_folder(training artifacts)mlflow_model_foldermlflow_model(fine-tuned model, ready for MLflow registry)Validation
End-to-end validated with AML job
maroon_horse_szbvr35pw1— training proceeds, parameters.yaml overrides apply correctly,last.ckpt→ safetensors conversion succeeds.Dependency
Important
Spec pins environment
acft-medimageparse-3d-finetune/versions/1, which is added by PR #5032. Component build will fail validation until that env PR merges. This PR should be merged after #5032.