## Requirements

```bash
pip install pythainlp
pip install gensim>=4.3.1
pip install git+https://github.com/openai/CLIP.git
```

## Usage

Encode a text by
```python
from transformers import AutoModel

text = 'หมากำลังวิ่งในสนามหญ้า'
model = AutoModel.from_pretrained("patomp/thai-light-multimodal-clip-and-distill", trust_remote_code=True)

embeddings = model(text)
print("Text features shape:", embeddings.shape)

```

Encode an image by
```python
import torch
import clip
import requests
from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
image = preprocess(image).unsqueeze(0).to(device)

with torch.no_grad():
    image_features = model.encode_image(image)

print("Image features shape:", image_features.shape) 
```

## Benchmark

On the test set of [Thai MS COCO 2014 dataset](https://huggingface.co/datasets/patomp/thai-mscoco-2014-captions)

| Model \ Metrics | text-find-image recall@1  | text-find-image recall@10 | image-find-text recall@1  | image-find-text recall@10  | # text samples per second* |
| :---  | --- | --- | --- | --- | --- |
| **Multilingual Encoder** | |   |   |   | |
| [clip-ViT-B-32-multilingual-v1](https://huggingface.co/sentence-transformers/clip-ViT-B-32-multilingual-v1) | 0.075 | 0.242 | 0.096 | 0.286 | 251 |
| [XLM-Roberta-Large-Vit-B-32](https://huggingface.co/M-CLIP/XLM-Roberta-Large-Vit-B-32) | **0.226** | **0.565** | **0.265** | **0.596** | 20 |
| **Thai Encoder (WangchanBERTa-based)**   |  |  |   |  |  |
| [Thai-Cross-CLIP](https://github.com/vikimark/Thai-Cross-CLIP) | 0.167 | 0.475 | 0.197  | 0.523  | 48 |
| **Thai Encoder (Thai2Fit-based)**  |  |  |   |  | |
| [thai-light-multimodal-clip-and-distill](https://huggingface.co/patomp/thai-light-multimodal-clip-and-distill) | 0.082  | **0.328** | 0.118 |**0.401**| 450 |
| [thai-light-multimodal-distill](https://huggingface.co/patomp/thai-light-multimodal-distill) | **0.084**  | 0.319 | **0.122** |**0.401**| 450 |

## Reference

Some part of this content referenced from  https://huggingface.co/M-CLIP/XLM-Roberta-Large-Vit-B-32. 

For more detail, please visit https://github.com/calzonelover/Lightweight-Multi-modal-Encoder-for-Thai.