SnapNature: Identify Nature with Open-Source AI — Touch Grass Challenge

Описание и применение

SnapNature — это PWA, позволяющая быстро и приватно идентифицировать растения и животных, используя открытые модели HuggingFace, работая офлайн.

Задача

Users want a mobile-friendly way to identify plants, animals, and natural scenes without relying on proprietary APIs or internet connectivity.

Результат

SnapNature enables instant, privacy‑first nature identification on any device, offline, with open‑weight models and easy model swapping.

Рабочий процесс

• Take a photo of a natural object
• Upload or capture image in the web interface
• Send image to HuggingFace ViT model for inference
• Receive top‑5 predictions with confidence scores
• Display educational facts and store observation in local journal
• Optionally swap the model for fine‑tuned regional models

Доказательства

SnapNature uses a pre-trained ResNet50 model (ImageNet) to classify images.

Источник

Take a photo of any plant, animal, or nature scene

Источник

Works offline via Service Worker — go to a trail, no signal needed

Источник