Chinese Clip Vit Large Patch14 336px

🚀 Chinese-CLIP-ViT-Large-Patch14-336px

This is a large-scale Chinese CLIP model that combines a ViT-L/14@336px image encoder with a RoBERTa-wwm-base text encoder, enabling effective processing of Chinese image-text pairs.

🚀 Quick Start

This is the large-version of the Chinese CLIP, with ViT-L/14@336px as the image encoder and RoBERTa-wwm-base as the text encoder. Chinese CLIP is a simple implementation of CLIP on a large-scale dataset of around 200 million Chinese image-text pairs. For more details, please refer to our technical report https://arxiv.org/abs/2211.01335 and our official github repo https://github.com/OFA-Sys/Chinese-CLIP (Welcome to star! 🔥🔥)

✨ Features

• Large-scale Dataset: Trained on approximately 200 million Chinese image-text pairs.
• Dual Encoders: Utilizes ViT-L/14@336px for image encoding and RoBERTa-wwm-base for text encoding.

💻 Usage Examples

Basic Usage

from PIL import Image
import requests
from transformers import ChineseCLIPProcessor, ChineseCLIPModel

model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-large-patch14-336px")
processor = ChineseCLIPProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-large-patch14-336px")

url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
# Squirtle, Bulbasaur, Charmander, Pikachu in English
texts = ["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]

# compute image feature
inputs = processor(images=image, return_tensors="pt")
image_features = model.get_image_features(**inputs)
image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True)  # normalize

# compute text features
inputs = processor(text=texts, padding=True, return_tensors="pt")
text_features = model.get_text_features(**inputs)
text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)  # normalize

# compute image-text similarity scores
inputs = processor(text=texts, images=image, return_tensors="pt", padding=True)
outputs = model(**inputs)
logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1)  # probs: [[0.0219, 0.0316, 0.0043, 0.9423]]

Advanced Usage

If you are not satisfied with only using the API, feel free to check our github repo https://github.com/OFA-Sys/Chinese-CLIP for more details about training and inference.

📚 Documentation

Results

MUGE Text-to-Image Retrieval

Flickr30K-CN Retrieval

COCO-CN Retrieval

Zero-shot Image Classification

📄 License

No license information provided in the original document.

📚 Citation

If you find Chinese CLIP helpful, feel free to cite our paper. Thanks for your support!

@article{chinese-clip,
  title={Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese},
  author={Yang, An and Pan, Junshu and Lin, Junyang and Men, Rui and Zhang, Yichang and Zhou, Jingren and Zhou, Chang},
  journal={arXiv preprint arXiv:2211.01335},
  year={2022}
}