Python package and CLI that simplifies using the BioCLIP family of foundation models.

Tree seedling detection and species identification using YOLO + BioCLIP

Deep learning fish classifier combining ConvNeXt-Tiny (40 species, 98.96% accuracy) with BioCLIP-2 zero-shot recognition and AI-powered habitat mapping

Mushroom for Improvement: Prototypical Few-Shot Learning with Multimodal Fungal Features - FungiCLEF25 @ CVPR-FGVC & LifeCLEF

BioCLIP base model for use with Autodistill.

A Python tool for estimating animal GPS coordinates from camera-trap imagery using known camera position, bearing, and pinhole geometric projection. Uses YOLO+SAHI sliced inference for detection and BioCLIP 2 (via open_clip) for zero-shot species classification.

Centralized resource to describe and link out to all components of the BioCLIP project (Code, Models, Datasets, Spaces).

Open-source biological image and video identification with BioCLIP retrieval, taxonomy constraints, and explainable multimodal reasoning.

Repository featuring all additional content for Luka Kowalchuk's MSc Thesis on: A Comparative Evaluation of Vision Transformer and Convolutional Neural Network Performance for Forensically Relevant Dipteran Classification

BlueSky bot account that bring happiness to BlueSky users

A CLIP model training recipe for classifying aquatic invertebrates.

Lightweight BioCLIP image search service using source URLs, FAISS, and DuckDB. Find the most visually similar images across 200M+ samples from the TreeofLife dataset.

Local backyard wildlife webcam rig - motion-gated MegaDetector v6 capture with species ID, individual re-ID, behaviour clips, and a live dashboard.

Distills BioCLIP 2.5 Huge (ViT-H/14, 632M params) into an 11.6M param FastViT student for on-device plant ID. 71.7% top-1 teacher agreement, 23.8 MB fp16 ONNX.