Blip Base Captioning Ft Hl Scenes

🚀 BLIP-base：針對場景高級描述圖像字幕微調模型

本模型基於 BLIP base，在 HL 數據集 上進行訓練，用於圖像場景生成。

🚀 快速開始

模型微調 🏋️‍

• 訓練輪數：10 輪
• 學習率：5e−5
• 優化器：Adam 優化器
• 精度：半精度（fp16）

測試集指標 🧾

模型使用示例 🚀

import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("michelecafagna26/blip-base-captioning-ft-hl-scenes")
model = BlipForConditionalGeneration.from_pretrained("michelecafagna26/blip-base-captioning-ft-hl-scenes").to("cuda")

img_url = 'https://datasets-server.huggingface.co/assets/michelecafagna26/hl/--/default/train/0/image/image.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')


inputs = processor(raw_image, return_tensors="pt").to("cuda")
pixel_values = inputs.pixel_values

generated_ids = model.generate(pixel_values=pixel_values, max_length=50,
            do_sample=True,
            top_k=120,
            top_p=0.9,
            early_stopping=True,
            num_return_sequences=1)

processor.batch_decode(generated_ids, skip_special_tokens=True)

>>> "the picture is taken near a lake."

BibTex 和引用信息

@inproceedings{cafagna2023hl,
  title={{HL} {D}ataset: {V}isually-grounded {D}escription of {S}cenes, {A}ctions and
{R}ationales},
  author={Cafagna, Michele and van Deemter, Kees and Gatt, Albert},
  booktitle={Proceedings of the 16th International Natural Language Generation Conference (INLG'23)},
address = {Prague, Czech Republic},
  year={2023}
}

📄 許可證

本項目採用 Apache-2.0 許可證。