Modelpublic

meganariley/wildflower-classifier-v2

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes14downloads

Model Card

🌸 Wildflower Classifier v2

75 North American wildflower species classifier based on EfficientNet-B4, fine-tuned on 59,000+ iNaturalist research-grade photos.

⏳ Training in progress — model weights will appear here once training completes.

Details


Base model	google/efficientnet-b4
Dataset	meganariley/inat-wildflowers-75
Species	75 (28 plant families)
Training	Label smoothing 0.1, mixup α=0.2, cosine decay with warmup
Augmentation	RandomResizedCrop, flip, ±30° rotation, ColorJitter, GaussianBlur
Artifacts	Training bucket

Usage

python

from transformers import pipeline

classifier = pipeline("image-classification", model="meganariley/wildflower-classifier-v2", top_k=5)
result = classifier("path/to/wildflower.jpg")

Demo

Try it live: Wildflower Identifier

Generated by ML Intern

This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.

—Try ML Intern: https://smolagents-ml-intern.hf.space
—Source code: https://github.com/huggingface/ml-intern