- Introduced `fused_importance_with_axial.py` to evaluate the importance of Axial_Length in the fused-head model.
- Created JSON configurations for various experiments excluding zero-importance clinical features:
- `cd_solo_bilateral_dropzero.json`: Bilateral clinical-only evaluation.
- `cd_solo_single_dropzero.json`: Single-eye clinical-only evaluation.
- `ensemble_refugelike_ckpt_dropzero.json`: Ensemble model with dropped zero-importance features.
- `ensemble_single_refugelike_dropzero.json`: Single-eye ensemble model with dropped features.
- Introduced `bridge_attention_ceiling_check.py` for variance decomposition analysis on bridge attention configurations.
- Added `bridge_attention_readout.py` to perform per-tower gate and contribution readouts, including AUC sanity checks.
- Created multiple JSON configuration files for backbone replication experiments, including anonymous CV variants and basic backbones.
- Implemented sensitivity experiments to evaluate the impact of axial length inclusion and EfficientNetV2-M performance at higher resolutions.
- Added a memory probe script to assess GPU memory usage during training with EfficientNetV2-M.
- Introduced multiple regression experiment configurations targeting vf_md, including:
- cd_solo_reg_set.json: CD tower only regression setup.
- img_solo_reg_set.json: Image tower only regression setup.
- reg_head_epoch_sweep.json: Baseline regression sweeps at different epochs (50, 75, 100).
- reg_head_set.json: Various regression setups including baseline and OrthoBridge configurations.
- single_eye_reg.json: Single-eye regression setup for worst-eye aggregation analysis.
- Added ensemble configurations for OrthoBridge with different inner bridges:
- ortho_alts_ensemble.json: Ensemble tests with ConcatBridge, PairwiseAdditiveBridge, and GatedAdditiveBridge.
- ortho_alts_tritower.json: Tritower tests with the same inner bridges.
- Created V2-M specific configurations:
- baseline_reg_nt50.json: Regression baseline with V2-M backbone.
- geom_vec_gt.json and geom_vec_unet.json: Geometry vector injection experiments with V2-M.
- single_l1_bridges.json: Single-eye ensemble experiments with various bridge types.
- tritower_geom_gt.json: Tritower setup with GT contour-rasterized masks.
- Promoted existing experiments to higher repetitions for robustness.
- Introduced `poster_model_comparison.py` for generating model comparison figures.
- Added `plot_poster_roc_comparison.py` for creating ROC comparison figures for PAPILA binary classification.
- Created new JSON configuration files for clinical solo models with and without geometry injection.
- Implemented batch dispatch updates in `batch_dispatch.py` to utilize run names from configurations.
- Added analysis scripts: `compare_grid.py`, `inspect_embeddings.py`, and `summarize_run.py` for evaluating model performance and feature embeddings.
- Created experiment configurations for various training scenarios, including warm sweeps and promoting successful runs.
- Added binary ROC comparison and model comparison figures to the results directory.
- Updated GTGeometryLoader to streamline geometry vector computation and caching.
- Introduced UNetGeometryLoader for UNet-derived geometry vectors.
- Added sample collection method in PapilaBundle for better data handling.
- Refined GeometrySegEncoder and ImageEncoder to utilize new sample collection.
- Enhanced distributed client with heartbeat mechanism for improved job tracking.
- Added new configuration files for UNet-derived geometry integration.
- Introduced `protocol.py` for shared data models used in server/client communication, including request and response schemas for registration, job submission, and status updates.
- Implemented `server.py` to manage a SQLite job queue and client registry, handling job polling, status updates, and job completion.
- Created a cheat sheet for server usage, detailing commands for starting the server, submitting jobs, and monitoring clients.
- Added several experiment configuration files for various training setups, including geometry vector injections and baseline ensembles.
rpotter6298