This project aims to provide a better Chinese CLIP model. The training data used in this project consists of publicly accessible image URLs and related Chinese text descriptions, totaling 400 million. After screening, we ultimately used 100 million data for training.
This project is produced by QQ-ARC Joint Lab, Tencent PCG. We have also open-sourced our code on GitHub,
QA-CLIP
, and welcome to star!
Models and Results
Model Card
QA-CLIP currently has three different open-source models of different sizes, and their model information and download links are shown in the table below:
We conducted zero-shot tests on
MUGE Retrieval
,
Flickr30K-CN
, and
COCO-CN
datasets for image-text retrieval tasks. For the image zero-shot classification task, we tested on the ImageNet dataset. The test results are shown in the table below:
Flickr30K-CN Zero-shot Retrieval (Official Test Set)
:
We have open-sourced our model on the HuggingFace for easier access and utilization. Additionally, we have prepared a simple online demo for zero-shot classification, allowing everyone to experience it firsthand. We encourage you to give it a try!
QA-CLIP huggingface.co is an AI model on huggingface.co that provides QA-CLIP's model effect (), which can be used instantly with this TencentARC QA-CLIP model. huggingface.co supports a free trial of the QA-CLIP model, and also provides paid use of the QA-CLIP. Support call QA-CLIP model through api, including Node.js, Python, http.
QA-CLIP huggingface.co is an online trial and call api platform, which integrates QA-CLIP's modeling effects, including api services, and provides a free online trial of QA-CLIP, you can try QA-CLIP online for free by clicking the link below.
TencentARC QA-CLIP online free url in huggingface.co:
QA-CLIP is an open source model from GitHub that offers a free installation service, and any user can find QA-CLIP on GitHub to install. At the same time, huggingface.co provides the effect of QA-CLIP install, users can directly use QA-CLIP installed effect in huggingface.co for debugging and trial. It also supports api for free installation.