ux-decoder/llava-grounding issues and pull requests

#26 - Understanding training mechanism of visual prompting module

Issue - State: open - Opened by Germany321 3 months ago

#26 - Understanding training mechanism of visual prompting module

Issue - State: open - Opened by Germany321 3 months ago

#25 - 缺少配置文件

Issue - State: open - Opened by yhl41001 6 months ago

#25 - 缺少配置文件

Issue - State: open - Opened by yhl41001 6 months ago

#24 - About the minimal GPU requirement

Issue - State: open - Opened by zhengyuan-xie 6 months ago

#24 - About the minimal GPU requirement

Issue - State: open - Opened by zhengyuan-xie 6 months ago

#23 - Config files do not exist

Issue - State: open - Opened by wusize 7 months ago - 1 comment

#23 - Config files do not exist

Issue - State: open - Opened by wusize 7 months ago - 1 comment

#22 - where is openseed_swint_lang_joint_2st_visual_prompt.yaml

Issue - State: open - Opened by husonchen 8 months ago

#22 - where is openseed_swint_lang_joint_2st_visual_prompt.yaml

Issue - State: open - Opened by husonchen 8 months ago

#21 - Cannot find the scripts to generate the grounded_visual_chat_data for COCO

Issue - State: open - Opened by YatingPan 8 months ago

#21 - Cannot find the scripts to generate the grounded_visual_chat_data for COCO

Issue - State: open - Opened by YatingPan 8 months ago

#20 - Could you please consider making the detailed production process of the GVC-R dataset public?

Issue - State: open - Opened by AugWrite 8 months ago

#20 - Could you please consider making the detailed production process of the GVC-R dataset public?

Issue - State: open - Opened by AugWrite 8 months ago

#19 - flick dataset has not the attribute segmentation error

Issue - State: open - Opened by garspace 9 months ago - 2 comments

#19 - flick dataset has not the attribute segmentation error

Issue - State: open - Opened by garspace 9 months ago - 2 comments

#18 - Evaluation on refcoco datasets.

Issue - State: open - Opened by juxingyiwan 9 months ago - 3 comments

#18 - Evaluation on refcoco datasets.

Issue - State: open - Opened by juxingyiwan 9 months ago - 3 comments

#17 - Link to config files are down

Issue - State: open - Opened by Yeon07 9 months ago - 1 comment

#17 - Link to config files are down

Issue - State: open - Opened by Yeon07 9 months ago - 1 comment

#16 - pretrain_joint miss the pretrain_mm_mlp_adapter

Issue - State: open - Opened by winboyer 10 months ago

#16 - pretrain_joint miss the pretrain_mm_mlp_adapter

Issue - State: open - Opened by winboyer 10 months ago

#15 - Demo is down

Issue - State: open - Opened by timabdulla 10 months ago - 1 comment

#15 - Demo is down

Issue - State: open - Opened by timabdulla 10 months ago - 1 comment

#14 - Visual prompt `pretrain weight` does not match

Issue - State: open - Opened by felixfuu 10 months ago

#13 - Could you please release the checkpoints for stages 1 and 2?

Issue - State: open - Opened by joslefaure 10 months ago

#13 - Could you please release the checkpoints for stages 1 and 2?

Issue - State: open - Opened by joslefaure 10 months ago

#12 - Can not find files like 'coco/annotations/instances_train2017_refcoco.json' and 'coco/annotations/grounding_train2017_instruct.json'.

Issue - State: open - Opened by gkw0010 10 months ago - 1 comment

#12 - Can not find files like 'coco/annotations/instances_train2017_refcoco.json' and 'coco/annotations/grounding_train2017_instruct.json'.

Issue - State: open - Opened by gkw0010 10 months ago - 1 comment

#11 - The trouble of visual prompt

Issue - State: closed - Opened by Vilonge 10 months ago - 1 comment

#10 - Missing dataset for pretraining

Issue - State: closed - Opened by juxingyiwan 10 months ago - 4 comments

#9 - When will the code and dataset be released?

Issue - State: closed - Opened by liuheng92 11 months ago - 1 comment

#8 - online demo returns error

Issue - State: closed - Opened by linhaojia13 11 months ago - 2 comments

#7 - Where is the inference code?

Issue - State: closed - Opened by Ryosuke0104 11 months ago - 2 comments

#6 - Where mask2former/modeling/pixel_decoder/ops ?

Issue - State: closed - Opened by Ryosuke0104 11 months ago - 1 comment

#5 - How to use `gd_ls` ?

Issue - State: closed - Opened by felixfuu 11 months ago - 1 comment

#4 - Visual Grounding Prompt

Issue - State: closed - Opened by lxiaohaung 11 months ago - 3 comments

#3 - Release of training data and training code

Issue - State: closed - Opened by lizhaoliu-Lec 12 months ago - 1 comment

#2 - where can I find the details about "the implementation and LLM prompts used across different pipeline levels'' mentioned in section 4?

Issue - State: closed - Opened by guoyanan1g 12 months ago

#1 - Online demo failed

Issue - State: closed - Opened by Lucky-Lance 12 months ago - 1 comment

GitHub / ux-decoder/llava-grounding issues and pull requests