Leaf Disease Nsdsr: 2,501 Images of Plant Diseases for Object Detection

Leaf Disease Nsdsr is an object detection dataset containing 2,501 annotated images of diseased leaves. It is part of the Roboflow 100 benchmark, a collection of 100 datasets spanning 7 imagery domains, and was authored by LibreYOLO. The dataset was last updated on January 20, 2026.

Use Cases

• Training object detection models to identify mildew on leaves based on the annotated class.
• Benchmarking model performance on plant disease imagery as part of the Roboflow 100 collection.
• Developing automated plant health monitoring systems based on visual symptoms of disease.
• Fine-tuning models like LibreYOLO for specific agricultural use cases.

Strengths

• Contains 2,501 total images, providing a substantial base for model training.
• Includes a clear split of 1,589 training, 616 validation, and 296 test images for structured evaluation.
• Focuses on three specific classes (mildew, rose_P01, rose_R02) for targeted detection tasks.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.
• The geographic and temporal coverage of the imagery is unknown, which may affect generalizability.

Provenance

Source

LibreYOLO

Collection Method

Part of the Roboflow 100 benchmark; likely collected and annotated for object detection tasks.

Time Range

null

Freshness

Last updated 2026-01-20 20:37:26; freshness should be verified.

Geography

null