Inception-ResNetV2 Prediction Probabilities for Peritoneal Metastasis

Prediction probabilities from an Inception-ResNetV2 model with different attention mechanisms. The data compares results at dropout probabilities of 0 and 0.3 on a test set for peritoneal metastasis. Chao Zhang published this 34.6 KB dataset under a CC-BY-4.0 license in May 2026.

Use Cases

• Compare model performance based on different attention mechanisms mentioned in the description
• Analyze the effect of dropout probability on prediction confidence for peritoneal metastasis
• Benchmark Inception-ResNetV2 model variants on a medical imaging task

Strengths

• Directly compares two dropout probabilities (0 and 0.3) for model evaluation
• Focuses on a specific medical condition (peritoneal metastasis) for targeted analysis
• Released under a permissive CC-BY-4.0 license for reuse

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

Chao Zhang

Collection Method

Likely contains prediction outputs from a trained Inception-ResNetV2 model.

Freshness

Last updated 2026-05-14 17:44:26; freshness should be verified