Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
SkiNet 1.0.0 documentation
SkiNet 1.0.0 documentation

Getting started

  • Software development process
  • Azure
  • Configuration guide

Data

  • Data
  • Datasets and dataloaders
  • Note about modification to PyTorch’s default dataloader

Model and training

  • Network Design
  • Training
  • Exporting to ONNX

Performance and debugging

  • Debugging
  • Plotting

Contributing

  • Documentation

Experiments

  • Experiments
    • E0 — Batch Size Sweep Analysis — UNet2D on ISIC 2017
    • E1 — ISIC 2017 UNet2D Architecture Sweep Summary (all Learning Rates)
    • E2 — ISIC 2017 UNet2D Architecture Tie-Break (10 seeds)
    • E3 — ISIC 2017 UNet2D LR-Schedule Tie-Break (10 seeds)
    • E4 — ISIC 2017 UNet2D Decision-Threshold Selection (10 seeds)
    • EF — ISIC 2017 UNet2D: held-out test score for the selected E4 checkpoint

API Reference

  • API Reference
    • Experiment Config
    • Lightning Model
    • Model Configs
    • Training Configs
    • Training Utilities
    • Transform Configs
    • Data Configs
    • Datasets API Reference
    • Logging and Callbacks
    • Experiment Keys
    • Optuna Utilities
Back to top
View this page

Experiments¶

  • E0 — Batch Size Sweep Analysis — UNet2D on ISIC 2017
  • E1 — ISIC 2017 UNet2D Architecture Sweep Summary (all Learning Rates)
  • E2 — ISIC 2017 UNet2D Architecture Tie-Break (10 seeds)
  • E3 — ISIC 2017 UNet2D LR-Schedule Tie-Break (10 seeds)
  • E4 — ISIC 2017 UNet2D Decision-Threshold Selection (10 seeds)
  • EF — ISIC 2017 UNet2D: held-out test score for the selected E4 checkpoint
Next
E0 — Batch Size Sweep Analysis — UNet2D on ISIC 2017
Previous
Documentation
Copyright © 2024, Pavel Kliuiev
Made with Sphinx and @pradyunsg's Furo