Shawn’s Blog
  • 🗂️ Collections
    • 🖥️ Slides Gallery
    • 🧑‍🍳️ Cooking Ideas
    • 🍱 Cookbook
    • 💬 Language Learning
    • 🎼 Songbook
  • ⚙️ Projects
    • ⚛ Continual Learning Arena
  • 📄 Papers
    • AdaHAT
    • FG-AdaHAT
  • 🎓 CV
    • CV (English)
    • CV (Mandarin)
  • About
  1. Continual Unlearning (CUL)
  2. Output Results
  • Welcome to CLArena
  • Get Started
  • Continual Learning (CL)
    • Configure CL Main Experiment
      • Experiment Index Config
      • CL Algorithm
      • CL Dataset
      • Backbone Network
      • Optimizer
      • Learning Rate Scheduler
      • Trainer
      • Metrics
      • Lightning Loggers
      • Callbacks
      • Other Configs
    • Save and Evaluate Model
    • Full Experiment
    • Output Results
  • Continual Unlearning (CUL)
    • Configure CUL Main Experiment
      • Experiment Index Config
      • Unlearning Algorithm
      • Callbacks
    • Full Experiment
    • Output Results
  • Multi-Task Learning (MTL)
    • Configure MTL Experiment
      • Experiment Index Config
      • MTL Algorithm
      • MTL Dataset
      • Backbone Network
      • Optimizer
      • Learning Rate Scheduler
      • Trainer
      • Metrics
      • Callbacks
    • Save and Evaluate Model
    • Output Results
  • Single-Task Learning (STL)
    • Configure STL Experiment
      • Experiment Index Config
      • STL Dataset
      • Backbone Network
      • Optimizer
      • Learning Rate Scheduler
      • Trainer
      • Metrics
      • Callbacks
    • Save and Evaluate Model
    • Output Results
  • Implement Your Modules (TBC)
  • API Reference

On this page

  • Output Results of CUL Main
  • Output Results of CUL Full Metrics Calculation
  1. Continual Unlearning (CUL)
  2. Output Results

Output Results (CUL)

Modified

August 16, 2025

This is a summary of what is included in the output results. Their existence, file or folder names, format of the output results can be customized.

Output Results of CUL Main

The following output results are produced after running clarena train culmain (with evaluation) or clarena eval culmain.

It is exact the same as the output results of CL Main experiment. Please refer to Output Results (CL) section. Please note that the difference is that some tasks are requested to be unlearned during the process.

Output Results of CUL Full Metrics Calculation

Full metric calculation results are produced only after clarena run cul or the separate clarena eval cl. Beyond the CL Main results, additional results include:

Folder or File Description Customization
<output_dir>/clrefretrain/ Contains all output results of the reference retraining learning experiment. Cannot be customized
<output_dir>/clreforiginal/ Contains all output results of the reference original learning experiment. Cannot be customized
<dd_save_dir>/ Contains all data and figures of DD metrics.
  • <dd_save_dir>: Field dd_save_dir in continual learning full metrics calculation experiment config. It is recommended to be set as ${output_dir}/xxx/ to make sure outputs are under <output_dir>/
<dd_save_dir>/dd.csv The original data of DD metrics, stored as CSV format.
  • dd.csv: Field dd_csv_name in continual learning full metrics calculation experiment config. Default is dd.csv.

  • If this is run under clarena run cul, it cannot be customized.

<dd_save_dir>/dd_plot.png A plot of DD.
  • dd_plot.png: Field dd_plot_name in continual learning full metrics calculation experiment config.
  • To exclude this output, set this field to null or remove this field.
  • If this is run under clarena run cul, it cannot be customized.
<ad_save_dir>/ Contains all data and figures of AD metrics.
  • <ad_save_dir>: Field ad_save_dir in continual learning full metrics calculation experiment config. It is recommended to be set as ${output_dir}/xxx/ to make sure outputs are under <output_dir>/
<ad_save_dir>/dd.csv The original data of AD metrics, stored as CSV format.
  • ad.csv: Field ad_csv_name in continual learning full metrics calculation experiment config. Default is ad.csv.

  • If this is run under clarena run cul, it cannot be customized.

<ad_save_dir>/ad_plot.png A plot of AD.
  • ad_plot.png: Field ad_plot_name in continual learning full metrics calculation experiment config.
  • To exclude this output, set this field to null or remove this field.
  • If this is run under clarena run cul, it cannot be customized.
Back to top
Full Experiment
Multi-Task Learning (MTL)
 
 

©️ 2025 Pengxiang Wang. All rights reserved.