Giters

encord-team / text-to-image-eval

Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN accuracy.

Home Page:https://encord.com

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Trouble adding `Qdrant/google-landmark-geo` Hugging Face geospatial dataset.

eloy-encord opened this issue · comments

commented

When adding the JSON definition of the Qdrant/google-landmark-geo Hugging Face dataset, got datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset.

JSON definition:

{
  "dataset_type": "HFDataset",
  "title": "geo-landmarks",
  "title_in_source": "Qdrant/google-landmark-geo"
}

Would worth investigating if the dataset is missing some customisation parameters in its definition or is ill-formed in Hugging Face.
It only has 5 downloads in the last month, so it could be broken or just very difficult to get ready.