Performance and Training Efficiency Comparison of Transformer and CNN Models

Md. Sifat Haque Zidan published a dataset on figshare in April 2026 comparing the performance and training efficiency of transformer baselines and proposed CNN models. The dataset is a 5.5 KB Excel file, suggesting a small-scale, focused comparison. It is licensed under CC-BY-4.0, allowing for open reuse.

Use Cases

• Benchmarking model performance based on the described comparison metrics.
• Analyzing training efficiency trade-offs between transformer and CNN architectures.
• Reproducing or validating experimental results from the associated research.

Strengths

• Dataset is small (5.5 KB), facilitating quick download and inspection.
• Licensed under CC-BY-4.0, providing clear permissions for reuse and modification.

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

Md. Sifat Haque Zidan via figshare.

Collection Method

Likely contains experimental results from model training and evaluation.

Time Range

Dataset was last updated in April 2026.

Freshness

Last updated 2026-04-24 17:24:12; freshness should be verified.

Geography

null