import torch
import pickle
from image_captioning_model import ImageCaptioningModel

with open("vocab.pkl", "rb") as f:
    vocab = pickle.load(f)

model = ImageCaptioningModel(
    vocab_size=len(vocab),
    pad_id=vocab.word2idx["<pad>"],
    use_vit=True
)

state_dict = torch.load("best_model.pth", map_location="cpu")
model.load_state_dict(state_dict)
model.eval()

---
license: mit
---

---
Author: Mostafa Hagali
---

mostafahagali/image-captioning-vit-transformer

Image Captioning with Vision Transformers

🚀 Demo

🧠 Architecture

📊 Training

📦 Files

🛠️ Usage

mostafahagali/
image-captioning-vit-transformer