Edible Mushroom Images for Classification Model Training

AWPF-ResNet18, a classification model incorporating an Adaptive Window Pyramid Fusion module, achieved a 2.5% accuracy improvement over the original ResNet18 on this dataset. The dataset likely contains images of edible mushrooms used to train and validate the model, which was authored by Xinhai Zhao and uploaded to figshare in April 2026.

Use Cases

• Training image classification models to distinguish edible mushroom varieties based on visual features mentioned in the description
• Benchmarking novel computer vision architectures like AWPF-ResNet18 against standard models based on mushroom images
• Developing safety tools for mushroom identification to prevent accidental poisoning based on the classification task described

Strengths

• Dataset is associated with a published model achieving a 2.5% accuracy improvement over ResNet18
• Model performance metrics (Acc, MP, MF, MR) are reported with specific percentage increases
• Data is openly licensed under CC-BY-4.0

Limitations

• Dataset size is only 5.5 KB, suggesting a very limited number of images or features
• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment

Provenance

Source

figshare

Freshness

Last updated 2026-04-16 17:31:42; freshness should be verified