# RaspberrySet: Raspberry (Rubus idaeus) Bud, Flower and Berry Ripeness Bounding Boxes in 2,039 iPhone Images, Latvia (Institute of Horticulture, AgML Mirror)

## Facts

- Provider: Sarmīte Strautiņa, Ieva Kalniņa, Edīte Kaufmane, Kaspars Sudars, Ivars Namatēvs and Artūrs Ņikuļins (Institute of Horticulture and Institute of Electronics and Computer Science, Latvia); Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://zenodo.org/records/7014728)
- Size: 6 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/raspberry_maturity_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.7014728
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/raspberry_maturity_detection
- Page: https://scigantic.com/archive/ce6a5427-b218-524b-acb2-34c5da1de211
- Keywords: Agriculture & Environment, Parquet, Hugging Face

## About

RaspberrySet holds 2,039 images (1773 x 1773 pixels, iPhone XS) of red raspberry (Rubus idaeus) plants at four development stages, taken at the Institute of Horticulture in Dobele, Latvia, between June and August 2021. Experts drew 46,659 boxes with LabelImg in YOLO format across five classes: bud (11,788), flower (4,748), unripe berry (29,156), ripe berry (463) and damaged bud (504). Useful for flowering and fruit-set monitoring, ripeness detection, yield forecasting and robotic harvesting of soft fruit. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/raspberry_maturity_detection") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: CC BY 4.0, as stated by the original publisher; cite Sarmīte Strautiņa, Ieva Kalniņa, Edīte Kaufmane, Kaspars Sudars, Ivars Namatēvs and Artūrs Ņikuļins et al. and the DOI 10.5281/zenodo.7014728.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("Project-AgML/raspberry_maturity_detection")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00004.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/ce6a5427-b218-524b-acb2-34c5da1de211
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ce6a5427-b218-524b-acb2-34c5da1de211
- Over MCP: `get_schema_card` with id `ce6a5427-b218-524b-acb2-34c5da1de211` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Agriculture & Environment datasets](https://scigantic.com/topics/agriculture-and-environment)
