metadata
license: apache-2.0
pipeline_tag: any-to-any
This repository contains the models of the paper Generalized Decoding for Pixel, Image, and Language.
Github: https://github.com/microsoft/X-Decoder
Click to Download!
-> Models
Focal-T:
xdecoder_focalt_last_novg.pt
xdecoder_focalt_last.pt
xdecoder_focalt_best_openseg.pt
Focal-L:
xdecoder_focall_last.pt
xdecoder_focall_bestseg.pt
-> Datasets
caption_class_similarity.pth
captions_train2017_filtrefgumdval_filtvlp.json
grounding_train2017_filtrefgumdval_filtvlp.json
panoptic_train2017_filtrefgumdval_filtvlp.json
refcocog_umd_val.json