--- license: apache-2.0 --- # Chinese-CLIP-Base ## Introduction This is the base-version of the Chinese CLIP. 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 ## Use with the official API We provide a simple code snippet to show how to use the API for Chinese-CLIP. For starters, please install cn_clip: ```bash # to install the latest stable release pip install cn_clip # or install from source code cd Chinese-CLIP pip install -e . ``` After installation, use Chinese CLIP as shown below: ```python import torch from PIL import Image import cn_clip.clip as clip from cn_clip.clip import load_from_name, available_models print("Available models:", available_models()) # Available models: ['ViT-B-16', 'ViT-L-14', 'ViT-L-14-336', 'ViT-H-14', 'RN50'] device = "cuda" if torch.cuda.is_available() else "cpu" model, preprocess = load_from_name("ViT-B-16", device=device, download_root='./') model.eval() image = preprocess(Image.open("examples/pokemon.jpeg")).unsqueeze(0).to(device) text = clip.tokenize(["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]).to(device) with torch.no_grad(): image_features = model.encode_image(image) text_features = model.encode_text(text) # Normalize the features. Please use the normalized features for downstream tasks. image_features /= image_features.norm(dim=-1, keepdim=True) text_features /= text_features.norm(dim=-1, keepdim=True) logits_per_image, logits_per_text = model.get_similarity(image, text) probs = logits_per_image.softmax(dim=-1).cpu().numpy() print("Label probs:", probs) # [[1.268734e-03 5.436878e-02 6.795761e-04 9.436829e-01]] ``` However, 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.

## Results ### MUGE Text-to-Image Retrieval
SetupZero-shotFinetune
MetricR@1R@5R@10MRR@1R@5R@10MR
WukongViT-B33.459.369.754.139.266.977.461.2
R2D2ViT-B----47.475.183.568.7
CN-CLIPViT-B52.176.784.471.158.483.690.077.4
### Flickr30K-CN Retrieval
TaskText-to-ImageImage-to-Text
SetupZero-shotFinetuneZero-shotFinetune
MetricR@1R@5R@10R@1R@5R@10R@1R@5R@10R@1R@5R@10
WukongViT-B45.773.882.267.689.694.266.288.794.383.997.699.0
R2D2ViT-B---78.394.697.0---92.699.199.8
CN-CLIPViT-B62.786.992.879.194.897.474.693.597.193.599.099.5
### COCO-CN Retrieval
TaskText-to-ImageImage-to-Text
SetupZero-shotFinetuneZero-shotFinetune
MetricR@1R@5R@10R@1R@5R@10R@1R@5R@10R@1R@5R@10
WukongViT-B49.279.487.967.091.496.748.377.888.865.890.396.6
R2D2ViT-B---75.194.298.1---76.195.398.5
CN-CLIPViT-B62.286.694.977.097.199.057.084.193.677.496.298.9

## 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} } ```