🚀 nlpconnect/vit - gpt2 - 图像描述生成

这是一个图像描述生成模型，由@ydshieh在[flax](https://github.com/huggingface/transformers/tree/main/examples/flax/image - captioning)中训练得到，此为[该模型](https://huggingface.co/ydshieh/vit - gpt2 - coco - en - ckpts)的PyTorch版本。该模型可将图像转换为文本描述，为图像赋予语义信息，在图像理解和信息提取等方面具有重要价值。

🚀 快速开始

模型信息

示例展示

• 稀树草原
• [足球比赛](https://huggingface.co/datasets/mishig/sample_images/resolve/main/football - match.jpg)
• 机场

相关文章

[使用Transformer进行图像描述生成的图解](https://ankur3107.github.io/blogs/the - illustrated - image - captioning - using - transformers/)


💻 使用示例

基础用法

from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
import torch
from PIL import Image

model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
def predict_step(image_paths):
  images = []
  for image_path in image_paths:
    i_image = Image.open(image_path)
    if i_image.mode != "RGB":
      i_image = i_image.convert(mode="RGB")

    images.append(i_image)

  pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
  pixel_values = pixel_values.to(device)

  output_ids = model.generate(pixel_values, **gen_kwargs)

  preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
  preds = [pred.strip() for pred in preds]
  return preds


predict_step(['doctor.e16ba4e4.jpg']) # ['a woman in a hospital bed with a woman in a hospital bed']

高级用法

from transformers import pipeline

image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")

image_to_text("https://ankur3107.github.io/assets/images/image-captioning-example.png")

# [{'generated_text': 'a soccer game with a player jumping to catch the ball '}]

📄 许可证

本项目采用Apache - 2.0许可证。

📞 联系信息

若需要任何帮助，可通过以下方式联系：

• Hugging Face
• Twitter
• GitHub
• LinkedIn