Hugging Face's logo

internetoftim
/
dinov2-base

Image Feature Extraction
Transformers
PyTorch
vit
Inference Endpoints
Model card Files Community
Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

To fine-tuning Details

nielsr/dinov2-base # pre-trained model from which to fine-tune

Graphcore/vit-base-ipu # config specific to the IPU (Used POD4)

How to use in IPU: https://huggingface.co/internetoftim/dinov2-base/blob/main/image_classification-dinov2-base.ipynb

Run the notebooks in this repository: Run on Gradient

Poplar SDK: v3.2.1

Dataset:

load a custom dataset from local/remote files or folders using the ImageFolder feature option 1: local/remote files (supporting the following formats: tar, gzip, zip, xz, rar, zstd) url = "https://madm.dfki.de/files/sentinel/EuroSAT.zip" files = list(Path(dataset_dir).rglob("EuroSAT.zip"))

Ask for help in GC Slack

Downloads last month
86
Inference API (serverless) does not yet support transformers models for this pipeline type.