# clipseg-rd64-refined
---


## README([From Huggingface](https://huggingface.co/CIDAS/clipseg-rd64-refined))



# CLIPSeg model 

CLIPSeg model with reduce dimension 64, refined (using a more complex convolution). It was introduced in the paper [Image Segmentation Using Text and Image Prompts](https://arxiv.org/abs/2112.10003) by Lüddecke et al. and first released in [this repository](https://github.com/timojl/clipseg). 

# Intended use cases

This model is intended for zero-shot and one-shot image segmentation.

# Usage

Refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/clipseg).



## Model Files

- [README.md](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/README.md) (596.0 B)

- [config.json](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/config.json) (4.7 KB)

- [merges.txt](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/merges.txt) (512.4 KB)

- [model_state.pdparams](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/model_state.pdparams) (575.1 MB)

- [preprocessor_config.json](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/preprocessor_config.json) (427.0 B)

- [special_tokens_map.json](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/special_tokens_map.json) (472.0 B)

- [tokenizer.json](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/tokenizer.json) (2.1 MB)

- [tokenizer_config.json](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/tokenizer_config.json) (954.0 B)

- [vocab.json](https://paddlenlp.bj.bcebos.com/models/community/CIDAS/clipseg-rd64-refined/vocab.json) (842.1 KB)


[Back to Main](../../)