---
license: apache-2.0
datasets:
- hl-scenes

library_name: pytorch
tags:
- pytorch
- image-to-text
---

# Model Card: VinVL for Captioning 🖼️

[Microsoft's VinVL](https://github.com/microsoft/Oscar) base fine-tuned on [HL-scenes]() dataset for **scene description generation** downstream task.

# Model fine-tuning 🏋️‍

The model has been finetuned for 10 epoch on [HL-scenes]() dataset

# Test set metrics 📈

Obtained with beam size 5 and max lenght 20

| Bleu-1 | Bleu-2 | Bleu-3 | Bleu-4 | METEOR | ROUGE-L | CIDEr | SPICE |
|--------|--------|--------|--------|--------|---------|-------|-------|
|  0.68  |  0.55  |  0.45  |  0.36  |  0.36  |  0.63   |  1.42 |  0.40 |


# Usage and Installation:

More info about how to install and use this model can be found here: [michelecafagna26/VinVL
](https://github.com/michelecafagna26/VinVL)

# Feature extraction ⛏️

This model has a separate Visualbackbone used to extract features.
More info about:
- the model here: [michelecafagna26/vinvl_vg_x152c4](https://huggingface.co/michelecafagna26/vinvl_vg_x152c4)
- the usage here [michelecafagna26/vinvl-visualbackbone](https://github.com/michelecafagna26/vinvl-visualbackbone)

# Quick start: 🚀

```python
from transformers.pytorch_transformers import BertConfig, BertTokenizer
from oscar.modeling.modeling_bert import BertForImageCaptioning
from oscar.wrappers import OscarTensorizer

ckpt = "path/to/the/checkpoint"
device = "cuda" if torch.cuda.is_available() else "cpu"

# original code
config = BertConfig.from_pretrained(ckpt)
tokenizer = BertTokenizer.from_pretrained(ckpt)
model = BertForImageCaptioning.from_pretrained(ckpt, config=config).to(device)

# This takes care of the preprocessing
tensorizer = OscarTensorizer(tokenizer=tokenizer, device=device)

# numpy-arrays with shape (1, num_boxes, feat_size)
# feat_size is 2054 by default in VinVL
visual_features = torch.from_numpy(feat_obj).to(device).unsqueeze(0)

# labels are usually extracted by the features extractor
labels = [['boat', 'boat', 'boat', 'bottom', 'bush', 'coat', 'deck', 'deck', 'deck', 'dock', 'hair', 'jacket']]

inputs = tensorizer.encode(visual_features, labels=labels)
outputs = model(**inputs)

pred = tensorizer.decode(outputs)

# the output looks like this:
# pred = {0: [{'caption': 'in a library', 'conf': 0.7070220112800598]}
```

# Citations 🧾

This is the model used in:

```BibTeX
@misc{cafagna2022understanding,
  author = {Cafagna Michele and van Deemter Kees and Gatt Albert},
  title = {Understanding Cross-modal Interactions in V&L Models that Generate Scene Descriptions},
  doi = {10.48550/ARXIV.2211.04971},
  url = {https://arxiv.org/abs/2211.04971},
  keywords = {Computation and Language (cs.CL), Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International}
}

```


Please consider citing the original project and the VinVL paper

```BibTeX

@misc{han2021image,
      title={Image Scene Graph Generation (SGG) Benchmark}, 
      author={Xiaotian Han and Jianwei Yang and Houdong Hu and Lei Zhang and Jianfeng Gao and Pengchuan Zhang},
      year={2021},
      eprint={2107.12604},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@inproceedings{zhang2021vinvl,
  title={Vinvl: Revisiting visual representations in vision-language models},
  author={Zhang, Pengchuan and Li, Xiujun and Hu, Xiaowei and Yang, Jianwei and Zhang, Lei and Wang, Lijuan and Choi, Yejin and Gao, Jianfeng},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={5579--5588},
  year={2021}
}

```