Vilt B32 Finetuned Vqa

🚀 视觉与语言Transformer (ViLT)，在VQAv2上微调

视觉与语言Transformer (ViLT) 模型在 VQAv2 上进行了微调。该模型由Kim等人在论文 ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision 中提出，并首次在 此仓库 中发布。

声明：发布ViLT的团队并未为此模型撰写模型卡片，因此本模型卡片由Hugging Face团队撰写。

🚀 快速开始

你可以使用该原始模型进行视觉问答任务。

💻 使用示例

基础用法

from transformers import ViltProcessor, ViltForQuestionAnswering
import requests
from PIL import Image

# prepare image + question
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
text = "How many cats are there?"

processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")

# prepare inputs
encoding = processor(image, text, return_tensors="pt")

# forward pass
outputs = model(**encoding)
logits = outputs.logits
idx = logits.argmax(-1).item()
print("Predicted answer:", model.config.id2label[idx])

BibTeX引用

@misc{kim2021vilt,
      title={ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision}, 
      author={Wonjae Kim and Bokyung Son and Ildoo Kim},
      year={2021},
      eprint={2102.03334},
      archivePrefix={arXiv},
      primaryClass={stat.ML}
}

📄 许可证

本项目采用Apache-2.0许可证。