Chinese-CLIP

OpenAI CLIP 模型中文预训练版本。该项目使用了大规模的中文数据进行训练（~2亿图文数据），提供了多个规模的预训练模型和技术报告，让使用者仅通过几行代码就能完成中文图文特征提取和图文检索。

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)# 对特征进行归一化，请使用归一化后的图文特征用于下游任务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)  # 图文匹配概率 [[1.268734e-03 5.436878e-02 6.795761e-04 9.436829e-01]]