vit-gpt2-fa-image-captioning-flickr30k

作者 hezarai · 下载 0 · 点赞 0 · 更新 2023-11-04

A Persian image captioning model constructed from a ViT + GPT2 architecture trained on flickr30k-fa (created by Sajjad Ayoubi). The encoder (ViT) was initialized from https://huggingface.co/google/vit-base-patch16-224 and the decoder (GPT2) was initialized from https://huggingface.co/HooshvareLab/gpt2-fa .

Usage

pip install hezar
from hezar import Model

model = Model.load("hezarai/vit-gpt2-fa-image-captioning-flickr30k")
captions = model.predict("example_image.jpg")
print(captions)