metadata
license: apache-2.0
datasets:
- AterMors/wikiart_recaption
language:
- en
metrics:
- rouge
- bleu
- meteor
library_name: transformers
pipeline_tag: image-to-text
tags:
- captioning
- paintings
- art
- wikiart
base_model:
- microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft
- openai-community/gpt2
Image Captioning Model created with VisionEncoderDecoderModel architecture using "microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft" as image_encoder and "openai/gpt2" as text_decoder. It has been trained on a variant of the WikiArt dataset that can be found at "AterMors/wikiart_recaption".