Instructions to use huangdffs/dnbr-tagger-preview1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use huangdffs/dnbr-tagger-preview1 with timm:
import timm model = timm.create_model("hf-hub:huangdffs/dnbr-tagger-preview1", pretrained=True) - Transformers
How to use huangdffs/dnbr-tagger-preview1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="huangdffs/dnbr-tagger-preview1") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("huangdffs/dnbr-tagger-preview1") model = AutoModelForImageClassification.from_pretrained("huangdffs/dnbr-tagger-preview1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
A lightweight multilabel classifier trained on an arbitrary subset of nyanko7/danbooru2023. Trained for ~40M samples at native resolution ~238x238. Decent performance for its size.
- Downloads last month
- -