encord-team / text-to-image-eval Goto Github PK
View Code? Open in Web Editor NEWEvaluate 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
License: Apache License 2.0