comparison README.md @ 3:25bb80df7c0c draft default tip

planemo upload for repository https://github.com/goeckslab/gleam.git commit f0daa5846b336584c708d88f6d7f1b5ee8dc3093
author goeckslab
date Sat, 17 Jan 2026 22:53:42 +0000
parents a92f200d296e
children
comparison
equal deleted inserted replaced
2:b708d0e210e6 3:25bb80df7c0c
10 - Handles missing images via configurable strategies and produces transparent metrics plus plots in an interactive HTML report. 10 - Handles missing images via configurable strategies and produces transparent metrics plus plots in an interactive HTML report.
11 11
12 ## Inputs 12 ## Inputs
13 - `Training dataset (CSV/TSV)`: includes the label column and any feature columns; image columns should contain file paths that exist in the provided ZIP archives (or absolute paths). 13 - `Training dataset (CSV/TSV)`: includes the label column and any feature columns; image columns should contain file paths that exist in the provided ZIP archives (or absolute paths).
14 - Optional `Test dataset (CSV/TSV)`: if omitted, the tool performs train/validation/test splitting or k-fold CV. 14 - Optional `Test dataset (CSV/TSV)`: if omitted, the tool performs train/validation/test splitting or k-fold CV.
15 - Optional `Sample ID column`: when provided, related rows are grouped into the same split and cross-validation fold to reduce leakage.
15 - Optional `Image archive(s) (ZIP)`: one or more archives containing the image files referenced in the table. 16 - Optional `Image archive(s) (ZIP)`: one or more archives containing the image files referenced in the table.
16 - Optional overrides: text and image backbones, evaluation metric, quality preset, threshold for binary tasks, and extra hyperparameters (JSON/YAML string or file path). 17 - Optional overrides: text and image backbones, evaluation metric, quality preset, threshold for binary tasks, and extra hyperparameters (JSON/YAML string or file path).
17 18
18 ## Outputs 19 ## Outputs
19 - `output_html`: interactive training/evaluation report with metrics and visualizations across the available splits. 20 - `output_html`: interactive training/evaluation report with metrics and visualizations across the available splits.