PlantTom Dataset Training and Validation Parameters for LeafDet Model

PlantTom is a balanced dataset of 7,836 tomato leaf disease images across 8 distinct classes, compiled from various public sources to address class imbalance. The associated XLS file contains the training and validation parameter settings for the LeafDet object detection model, which is based on YOLOv8 architecture. The dataset and model were authored by Vaskor Mostafa and last updated on 2026-05 22.

Use Cases

• Reproducing the training of the LeafDet model based on the documented parameter settings
• Benchmarking object detection models for plant disease identification based on the described PlantTom dataset
• Studying the impact of architectural modules like C2f, SPPF, and attention mechanisms on model performance
• Investigating the use of loss functions like PIoUv2 for agricultural object detection tasks

Strengths

• Dataset is explicitly balanced to mitigate class imbalance issues common in public plant disease datasets
• The PlantTom dataset contains 7,836 images across 8 distinct tomato leaf disease classes
• The associated LeafDet model achieved a reported 91.6% [email protected] on this dataset

Limitations

• The XLS file is only 5.5 KB, suggesting it contains only parameter settings, not the image data itself
• Column-level documentation for the parameter file is absent; field semantics must be inferred after download
• The dataset's geographic and temporal coverage is not specified, which may limit understanding of its representativeness

Provenance

Source

Vaskor Mostafa via figshare

Collection Method

Images combined from various public sources to create the PlantTom dataset; parameters derived from model training.

Time Range

null

Freshness

Last updated 2026-05-22 18:00:31; freshness should be verified

Geography

null