clipseg-rd64-refined#
README(From Huggingface)#
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 by Lüddecke et al. and first released in this repository.
Intended use cases#
This model is intended for zero-shot and one-shot image segmentation.
Usage#
Refer to the documentation.
Model Files#
README.md (596.0 B)
config.json (4.7 KB)
merges.txt (512.4 KB)
model_state.pdparams (575.1 MB)
preprocessor_config.json (427.0 B)
special_tokens_map.json (472.0 B)
tokenizer.json (2.1 MB)
tokenizer_config.json (954.0 B)
vocab.json (842.1 KB)