CIDAS
/
clipseg-rd64-refined
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
CIDAS/clipseg-rd64-refined is a forked repo from huggingface. License: apache-2-0
8 Commits 1 Branch 0 Tags 576 MiB
Text 100%
Go to file
Niels Rogge 583b388deb Update preprocessor_config.json 2023-01-04 11:56:08 +00:00
.gitattributes initial commit 2022-11-01 14:25:57 +00:00
README.md Create README.md 2022-11-08 10:50:20 +00:00
config.json Upload CLIPSegForImageSegmentation 2022-11-07 14:02:59 +00:00
merges.txt Upload processor 2022-11-04 09:52:16 +00:00
preprocessor_config.json Update preprocessor_config.json 2023-01-04 11:56:08 +00:00
pytorch_model.bin Upload CLIPSegForImageSegmentation 2022-11-07 14:02:59 +00:00
special_tokens_map.json Upload processor 2022-11-04 09:52:16 +00:00
tokenizer_config.json Upload processor 2022-11-04 09:52:16 +00:00
vocab.json Upload processor 2022-11-04 09:52:16 +00:00

README.md

license tags inference
apache-2.0
vision
image-segmentation
false

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.