标签:

• 图像转文本
• 图像描述生成 许可证: Apache-2.0 演示样例:
• 图片: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg 示例标题: 热带草原
• 图片: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg 示例标题: 足球比赛
• 图片: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg 示例标题: 机场

使用Transformers实现图解图像描述生成

示例运行代码

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

model = VisionEncoderDecoderModel.from_pretrained("Ayansk11/Image_Caption_using_ViT_GPT2")
feature_extractor = ViTImageProcessor.from_pretrained("Ayansk11/Image_Caption_using_ViT_GPT2")
tokenizer = AutoTokenizer.from_pretrained("Ayansk11/Image_Caption_using_ViT_GPT2")

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']) # ['一位女士躺在病床上，旁边有位女士站在病床边']

使用Transformers流水线的示例代码

from transformers import pipeline

image_to_text = pipeline("image-to-text", model="Ayansk11/Image_Caption_using_ViT_GPT2")

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

# [{'generated_text': '足球比赛中球员跃起接球的场景'}]