Image Caption Using ViT GPT2

🚀 The Illustrated Image Captioning using transformers

This project uses transformers for image captioning, enabling the generation of text descriptions for images.

🚀 Quick Start

This project provides two ways to perform image captioning. You can use the custom function or the transformers pipeline.

💻 Usage Examples

Basic Usage

# Sample running code
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']) # ['a woman in a hospital bed with a woman in a hospital bed']

Advanced Usage

# Sample running code using transformers pipeline
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': 'a soccer game with a player jumping to catch the ball '}]

📄 License

This project is licensed under the Apache 2.0 license.