paligemma_Malaysian_plate_recognition

This model is a fine-tuned version of google/paligemma-3b-pt-224 on the Malaysian license plate dataset.

from PIL import Image
import torch
from transformers import PaliGemmaProcessor, PaliGemmaForConditionalGeneration, BitsAndBytesConfig, TrainingArguments, Trainer
import time

model = PaliGemmaForConditionalGeneration.from_pretrained('NYUAD-ComNets/VehiclePaliGemma',torch_dtype=torch.bfloat16)

input_text ="extract the text from the image"

processor = PaliGemmaProcessor.from_pretrained("google/paligemma-3b-pt-224")

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

model.to(device)

input_image = Image.open(image_path)
        
inputs = processor(text=input_text, images=input_image, padding="longest", do_convert_rgb=True, return_tensors="pt").to(device)
inputs = inputs.to(dtype=model.dtype)

with torch.no_grad():
     output = model.generate(**inputs, max_length=500)

result=processor.decode(output[0], skip_special_tokens=True)[len(input_text):].strip()

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 5

Framework versions

• Transformers 4.42.4
• Pytorch 2.1.2+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1

BibTeX entry and citation info

@article{aldahoul2025multitasking,
  title={Multitasking vision language models for vehicle plate recognition with VehiclePaliGemma},
  author={AlDahoul, Nouar and Tan, Myles Joshua Toledo and Tera, Raghava Reddy and Abdul Karim, Hezerul and Lim, Chee How and Mishra, Manish Kumar and Zaki, Yasir},
  journal={Scientific Reports},
  volume={15},
  number={1},
  pages={1--15},
  year={2025},
  publisher={Nature Publishing Group}
}


@misc{aldahoul2024advancingvehicleplaterecognition,
      title={Advancing Vehicle Plate Recognition: Multitasking Visual Language Models with VehiclePaliGemma}, 
      author={Nouar AlDahoul and Myles Joshua Toledo Tan and Raghava Reddy Tera and Hezerul Abdul Karim and Chee How Lim and Manish Kumar Mishra and Yasir Zaki},
      year={2024},
      eprint={2412.14197},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.14197}, 
}