lxtGH/OMG-Seg

Issues

• Inference error

  #28 opened 5 months ago by echo840
  9

• support for semantic segmentaion

  #57 opened 2 months ago by hansunhayden
  0

• Where is “convnext_large_d_320” in video_demo?

  #56 opened 2 months ago by lianhh1212
  2

• onnx

  #49 opened 3 months ago by hcscysh
  1

• How to fine-tune omg-seg on my own dataset?

  #53 opened 3 months ago by Oseemaker
  1

• About visual prompt object queries

  #41 opened 5 months ago by feivelliu
  0

• no OMG_LLaVA_README.md

  #55 opened 3 months ago by waziyyy
  0

• error when running the omg-llava demo

  #51 opened 4 months ago by abcjhby2871
  2

• omg-llava在区域性交互

  #54 opened 3 months ago by wyting98
  0

• GCG推理时无法批处理

  #52 opened 4 months ago by zhicong01
  0

• Changing vocabulary

  #42 opened 5 months ago by benakhovan32561
  1

• 关于运行推理相关代码时环境的问题

  #48 opened 4 months ago by zhicong01
  1

• Beam search in inference

  #50 opened 4 months ago by Germany321
  0

• Multi node training?

  #35 opened 4 months ago by echo840
  1

• question about demo

  #43 opened 4 months ago by ShelbyXu9
  1

• Demo Error

  #47 opened 4 months ago by SecretMG
  1

• image_demo.py

  #45 opened 4 months ago by hcscysh
  3

• demo is not work

  #46 opened 4 months ago by liyaowei-stu
  1

• 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.

  #44 opened 4 months ago by aimll101
  0

• GCG evaluation error

  #40 opened 5 months ago by ftfrz
  0

• When I train,an error occur

  #36 opened 5 months ago by aimll101
  1

• About the pretrained weights path

  #39 opened 5 months ago by ftfrz
  0

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

  #34 opened 5 months ago by placeforyiming
  3

• When I test,aTypeError occur.

  #38 opened 5 months ago by aimll101
  1

• error on omg llava iin gradio and hugging face

  #25 opened 5 months ago by Jayantverma2
  1

• Text prompt segmentation capability

  #37 opened 5 months ago by feivelliu
  1

• A small bug and question of eval code

  #27 opened 5 months ago by baibizhe
  1

• A terrible repository and demo

  #33 opened 5 months ago by YuetKaka15
  2

• A bug with size mismatch

  #30 opened 5 months ago by Butingg
  2

• Training code for image-based instance segmentation is same?

  #31 opened 5 months ago by pkyzh2006
  10

• Questions about the code

  #24 opened 5 months ago by chunshengshi
  2

• omgllava finetune阶段EvaluateChatHook输出的结果与图片不符？

  #29 opened 5 months ago by echo840
  0

• Why does model performance deteriorate when I unfreeze the decoder during training?

  #32 opened 5 months ago by echo840
  0

• convnext_large_d_320_th139_st101.pth

  #26 opened 6 months ago by hcscysh
  1

• Questions about Multi-Dataset Setting

  #10 opened 6 months ago by JiajiaLi04
  5

• multi-label for each point

  #9 opened 6 months ago by suliangxu
  4

• Why does this error occur when I run test.py

  #21 opened 6 months ago by xihao-1223
  5

• dist or dish?

  #22 opened 6 months ago by xihao-1223
  1

• How to increase vocabulary?

  #23 opened 6 months ago by lihengtao
  1

• test on one image

  #20 opened 6 months ago by hcscysh
  4

• Training Error: 'Naive_Proj' object has no attribute 'visual_prompt_zero'

  #19 opened 6 months ago by dddraxxx
  2

• About the image caption ability

  #18 opened 6 months ago by HarryHsing
  1

• How to export to ONNX

  #14 opened 6 months ago by anhquannguyen21
  2

• Env Installing Error

  #17 opened 6 months ago by dddraxxx
  1

• how to export onnx or trace pytorch model

  #13 opened 7 months ago by adrian-wl
  1

• clip backbone missing

  #11 opened 7 months ago by Yonggie
  5

• Huggingface loading is not valid

  #12 opened 7 months ago by Yonggie
  3

• Training

  #8 opened 9 months ago by yahooo-m
  3

• Reflective starring

  #7 opened 10 months ago by evdcush
  0

• Where is label of Object-365-instance segmentation

  #6 opened 10 months ago by ArsenLuca
  1