Model Performance Metrics for Training on Eclipsed Images

9.5 KB of tabular data in XLS format, authored by Yixi Xu and last updated on May 7, 2026. The dataset likely contains internal and external performance metrics for machine learning models trained on images with varying degrees of eclipse (extent = 0, 0.9, 1.0).

Use Cases

• Benchmarking model robustness based on performance metrics for eclipsed image training.
• Analyzing the relationship between data corruption extent and model generalization based on internal and external performance scores.
• Studying the effects of image preprocessing or augmentation on model performance based on the eclipse extent variable.

Strengths

• Data is openly licensed under CC-BY-4.0.
• File size is precisely 9.5 KB, indicating a compact and focused dataset.
• Update timestamp is specific to May 7, 2026, 17:30:08.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely contains experimental results from training models on a single source of images with simulated eclipses.

Time Range

null

Freshness

Last updated 2026-05-07 17:30:08; freshness should be verified.

Geography

null