lxtGH/OMG-Seg issues and pull requests

#50 - Beam search in inference

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

#49 - onnx

Issue - State: open - Opened by hcscysh 8 days ago

#48 - 关于运行推理相关代码时环境的问题

Issue - State: open - Opened by zhicong01 9 days ago - 1 comment

#47 - Demo Error

Issue - State: closed - Opened by SecretMG 16 days ago - 1 comment

#46 - demo is not work

Issue - State: closed - Opened by liyaowei-stu 16 days ago - 1 comment

#45 - image_demo.py

Issue - State: closed - Opened by hcscysh 17 days ago - 3 comments

#44 - How to make LLM output object-centered visual annotations without decoding the LLM's output, so that it does not generate text but only produces segmented images.

Issue - State: open - Opened by aimll101 20 days ago

#43 - question about demo

Issue - State: closed - Opened by ShelbyXu9 21 days ago - 1 comment

#42 - Changing vocabulary

Issue - State: open - Opened by benakhovan32561 23 days ago - 1 comment

#41 - About visual prompt object queries

Issue - State: open - Opened by feivelliu 25 days ago - 1 comment

#40 - GCG evaluation error

Issue - State: open - Opened by Namenameee 26 days ago - 5 comments

#39 - About the pretrained weights path

Issue - State: closed - Opened by Namenameee 27 days ago

#38 - When I test,aTypeError occur.

Issue - State: closed - Opened by aimll101 28 days ago - 1 comment

#37 - Text prompt segmentation capability

Issue - State: closed - Opened by feivelliu 29 days ago - 1 comment

#36 - When I train,an error occur

Issue - State: closed - Opened by aimll101 29 days ago - 1 comment

#35 - Multi node training?

Issue - State: closed - Opened by echo840 30 days ago - 1 comment

#34 - How to check the model result of OMG-LlaVa on a given image?

Issue - State: closed - Opened by placeforyiming 30 days ago - 3 comments

#33 - A terrible repository and demo

Issue - State: closed - Opened by YuetKaka15 about 1 month ago - 2 comments

#32 - Why does model performance deteriorate when I unfreeze the decoder during training?

Issue - State: closed - Opened by echo840 about 2 months ago

#31 - Training code for image-based instance segmentation is same?

Issue - State: closed - Opened by pkyzh2006 about 2 months ago - 10 comments

#30 - A bug with size mismatch

Issue - State: closed - Opened by Butingg about 2 months ago - 2 comments

#29 - omgllava finetune阶段EvaluateChatHook输出的结果与图片不符？

Issue - State: closed - Opened by echo840 about 2 months ago

#28 - Inference error

Issue - State: closed - Opened by echo840 about 2 months ago - 8 comments
Labels: bug

#27 - A small bug and question of eval code

Issue - State: closed - Opened by baibizhe about 2 months ago - 1 comment

#26 - convnext_large_d_320_th139_st101.pth

Issue - State: closed - Opened by hcscysh about 2 months ago - 1 comment

#25 - error on omg llava iin gradio and hugging face

Issue - State: closed - Opened by Jayantverma2 2 months ago - 1 comment

#24 - Questions about the code

Issue - State: closed - Opened by chunshengshi 2 months ago - 2 comments
Labels: bug, enhancement

#23 - How to increase vocabulary?

Issue - State: closed - Opened by lihengtao 2 months ago - 1 comment

#22 - dist or dish?

Issue - State: closed - Opened by xihao-1223 2 months ago - 1 comment

#21 - Why does this error occur when I run test.py

Issue - State: closed - Opened by xihao-1223 2 months ago - 5 comments
Labels: bug

#20 - test on one image

Issue - State: closed - Opened by hcscysh 2 months ago - 4 comments
Labels: documentation

#19 - Training Error: 'Naive_Proj' object has no attribute 'visual_prompt_zero'

Issue - State: closed - Opened by dddraxxx 2 months ago - 2 comments
Labels: bug

#18 - About the image caption ability

Issue - State: open - Opened by HarryHsing 3 months ago - 1 comment
Labels: enhancement

#17 - Env Installing Error

Issue - State: closed - Opened by dddraxxx 3 months ago - 1 comment

#16 - update omg_llava

Pull Request - State: closed - Opened by zhang-tao-whu 3 months ago

#15 - add omg llava codes

Pull Request - State: closed - Opened by zhang-tao-whu 3 months ago

#14 - How to export to ONNX

Issue - State: closed - Opened by anhquannguyen21 3 months ago - 2 comments

#13 - how to export onnx or trace pytorch model

Issue - State: closed - Opened by adrian-wl 3 months ago - 1 comment

#12 - Huggingface loading is not valid

Issue - State: open - Opened by Yonggie 3 months ago - 3 comments

#11 - clip backbone missing

Issue - State: closed - Opened by Yonggie 3 months ago - 5 comments

#10 - Questions about Multi-Dataset Setting

Issue - State: closed - Opened by JiajiaLi04 5 months ago - 5 comments
Labels: enhancement

#9 - multi-label for each point

Issue - State: closed - Opened by suliangxu 5 months ago - 4 comments
Labels: enhancement

#8 - Training

Issue - State: closed - Opened by yahooo-m 6 months ago - 3 comments
Labels: good first issue

#7 - Reflective starring

Issue - State: closed - Opened by evdcush 6 months ago

#6 - Where is label of Object-365-instance segmentation

Issue - State: closed - Opened by ArsenLuca 6 months ago - 1 comment

#5 - how to do inference on video or realtime ?

Issue - State: closed - Opened by Ahmed471996 6 months ago - 3 comments
Labels: enhancement

#4 - about inference code open source？

Issue - State: closed - Opened by xiyangyang99 8 months ago - 4 comments

#3 - Update DATASET.md

Pull Request - State: closed - Opened by eltociear 8 months ago

#2 - Update INSTALL.md

Pull Request - State: closed - Opened by eltociear 8 months ago

#1 - convnext_large_d_320_CocoPanopticOVDataset.pth

Issue - State: closed - Opened by Reginald-L 8 months ago - 4 comments

GitHub / lxtGH/OMG-Seg issues and pull requests