license: apache-2.0
pipeline_tag: feature-extraction
tags:
- clip
- zh
- image-text
- feature-extraction
Model Details
This model is a Chinese CLIP model trained on Noah-Wukong Dataset, which contains about 100M Chinese image-text pairs. We use ViT-L-14 from openAI as image encoder and Chinese pre-trained language model chinese-roberta-wwm-large as text encoder. We freeze the image encoder and only finetune the text encoder. The model was trained for 24 epochs and it takes about 12 days with 16 A100 GPUs.
Taiyi (太乙)
Taiyi models are a branch of the Fengshenbang (封神榜) series of models. The models in Taiyi are pre-trained with multimodal pre-training strategies. We will release more image-text model trained on Chinese dataset and benefit the Chinese community.
Usage
from PIL import Image
import requests
import clip
import torch
from transformers import BertForSequenceClassification, BertConfig, BertTokenizer
from transformers import CLIPProcessor, CLIPModel
import numpy as np
query_texts = ["一只猫", "一只狗",'两只猫', '两只老虎','一只老虎'] # 这里是输入文本的，可以随意替换。
# 加载Taiyi 中文 text encoder
text_tokenizer = BertTokenizer.from_pretrained("IDEA-CCNL/Taiyi-CLIP-Roberta-large-326M-Chinese")
text_encoder = BertForSequenceClassification.from_pretrained("IDEA-CCNL/Taiyi-CLIP-Roberta-large-326M-Chinese").eval()
text = text_tokenizer(query_texts, return_tensors='pt', padding=True)['input_ids']
url = "http://images.cocodataset.org/val2017/000000039769.jpg" # 这里可以换成任意图片的url
# 加载CLIP的image encoder
clip_model = CLIPModel.from_pretrained("openai/openai/clip-vit-large-patch14")
processor = CLIPProcessor.from_pretrained("openai/openai/clip-vit-large-patch14")
image = processor(images=Image.open(requests.get(url, stream=True).raw), return_tensors="pt")
with torch.no_grad():
image_features = clip_model.get_image_features(**image)
text_features = text_encoder(text).logits
# 归一化
image_features = image_features / image_features.norm(dim=1, keepdim=True)
text_features = text_features / text_features.norm(dim=1, keepdim=True)
# 计算余弦相似度 logit_scale是尺度系数
logit_scale = clip_model.logit_scale.exp()
logits_per_image = logit_scale * image_features @ text_features.t()
logits_per_text = logits_per_image.t()
probs = logits_per_image.softmax(dim=-1).cpu().numpy()
print(np.around(probs, 3))
Evaluation
Zero-Shot Classification
还没训练好，这里留空。预计还要一周。
| model | dataset | Top1 | Top5 |
|---|---|---|---|
| Taiyi-CLIP-Roberta-102M-Chinese | ImageNet1k-CN | 41.00% | 69.19% |
Zero-Shot Text-to-Image Retrieval
还没训练好，这里留空。预计还要一周。
| model | dataset | Top1 | Top5 | Top10 |
|---|---|---|---|---|
| Taiyi-CLIP-Roberta-102M-Chinese | COCO-CN | 25.47 % | 51.70% | 63.07% |
| Taiyi-CLIP-Roberta-102M-Chinese | wukong50k | 48.67 % | 81.77% | 90.09% |
Citation
If you find the resource is useful, please cite the following website in your paper.
@misc{Fengshenbang-LM,
title={Fengshenbang-LM},
author={IDEA-CCNL},
year={2022},
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}