iNatAg-mini
Project AgML
Working with a huge species image archive is impractical when you are still testing an idea. This is a smaller farming focused slice of a nature observation photo collection, covering crop and weed species recognition.
QUICK INFO
SOLUTION TYPE
Models, data & tools
TECHNOLOGY CATEGORY
Datasets & corpora
AREA OF WORK
Crop protection & plant health
ACCESS
Free · Open source
DEPLOYMENT
Cloud-hosted · Downloadable
SOURCE REVIEWED
August 17, 2026
What it helps with
- Small plant species image set for testing
- Identify a crop or weed from a photo
- Crop and weed species photos to download
- Try species recognition without a huge archive
- Train a plant identification model quickly
- Manageable slice of a species photo collection
Scope & audience
WHO IT'S FOR
Scientist / researcher · Developer / AI builder
AREA OF WORK
Crop protection & plant health
COMMODITY / SCOPE
Crop protection
Access & technical details
ACCESS
Anyone can get it
INTERFACE
API · Model download / weights
DEPLOYMENT
Hosted, you call it from your own code
LANGUAGES
Not stated by provider
Featured media
Source information
This listing was compiled from publicly available source material. Verify current details with the provider.
PROVIDER DOCUMENTATION
Reviewed August 2026
Explore more like this
CGIAR Agriculture Videos QnA2
CGIAR
Models, data & tools
Turning recorded farm training into something a model can learn from takes work. This is a downloadable set of question and answer records drawn from agricultural videos, for training or for checking answers.
Free
Self-hosted / on-premise · Downloadable
Datasets & corpora
CGIAR Agriculture Videos QnA2
advise-educate
extension-advisory-and-education
buildable-or-downloadable-component
datasets-and-corpora
Free
Self-hosted / on-premise · Downloadable
August 17, 2026
- Question and answer pairs from farm videos
- Reuse recorded farm training for a model
- Check assistant answers against video advice
- Turn farm video content into training data
- Ground a farm bot in advisory videos
- Training records from agricultural recordings
SYNTOM
Publisher not stated
Models, data & tools
Hand labelling tomato plant photos is tedious, so people try training on computer generated images instead. This is a downloadable set of synthetic tomato images for teaching models to outline plant parts, released with a study on adapting an image model.
Free
Self-hosted / on-premise · Downloadable
Datasets & corpora
SYNTOM
research-develop
seed-genetics-and-breeding
buildable-or-downloadable-component
datasets-and-corpora
Free
Self-hosted / on-premise · Downloadable
August 23, 2026
- Synthetic tomato plant images to download
- Train a model to outline tomato parts
- Avoid hand labelling tomato photos
- Tomato image dataset for segmentation
- Adapt an image model to tomatoes
Is this your Resource?
Contact us to claim this listing and add details, screenshots or a demo.