mbzuai-oryx/groundingLMM

Issues

• Issues in Shape Handling and Original Image Size

  #79 opened a month ago by gongshichina
  0

• can't train with the dataset(--use_reg_data --reg_dataset 'VisGen_Reg' --val_dataset 'VisGenomeRegVal')

  #78 opened a month ago by zhenze2
  0

• can't eval

  #77 opened a month ago by zhenze2
  0

• Online Demo is down again

  #73 opened 3 months ago by HAL-42
  1

• app.py error

  #76 opened a month ago by hanzefang
  0

• Can not download the train.json file for visual genome

  #59 opened 6 months ago by L1uShuai
  1

• Region input for demo

  #75 opened 2 months ago by 582383982
  2

• Offline demo error

  #66 opened 5 months ago by Roberyan
  1

• Potential Data Leakage?

  #74 opened 2 months ago by joshmyersdean
  1

• Can not find file for glamm_conda_env.zip in the given Google Drive Link

  #56 opened 6 months ago by PPPPPsanG
  5

• Online Demo Down

  #51 opened 6 months ago by Shengcao-Cao
  1

• Understanding predicting multiple masks

  #72 opened 3 months ago by joshmyersdean
  0

• can not install mmcv

  #55 opened 5 months ago by zhipeixu
  2

• OOM Error on 8xA100

  #71 opened 3 months ago by joshmyersdean
  1

• How can I finetune on combined tasks?

  #62 opened 6 months ago by Rubics-Xuan
  1

• The training losses in the GCG task

  #33 opened 9 months ago by gWeiXP
  2

• Question about eval pipeline on RefCOCO (doing sampling during evaluation).

  #70 opened 4 months ago by Z-MU-Z
  0

• Why is it that during the computation of segmentation results, the model() function is used instead of model.generate()? Wouldn't this mean that when predicting the next token, the information viewed is from the actual token rather than the predicted one?

  #67 opened 5 months ago by L1uShuai
  1

• How to Construct a Ground-Truth Test Dataset

  #69 opened 5 months ago by hungnh1125
  0

• What are the ‘categories’ in the dataset used for? When would I use them?

  #68 opened 5 months ago by bibibabibo26
  0

• AssertionError when running a demo

  #65 opened 5 months ago by suikei-wang
  0

• Confusing referring segmentation results.

  #63 opened 6 months ago by ZhimaoPeng
  1

• mmcv failed to install

  #64 opened 5 months ago by suikei-wang
  1

• How can I let the model receive multiple images at once

  #60 opened 6 months ago by bibibabibo26
  1

• How should I train on the GranD dataset

  #61 opened 6 months ago by Fangyi-Chen
  0

• training V-L and L-P projection layer

  #58 opened 6 months ago by remvanthull
  1

• Training on New Data

  #57 opened 6 months ago by ajb8866
  2

• About region caption

  #48 opened 8 months ago by mu-jin-meng
  2

• 3D implementation of GLaMM

  #46 opened 6 months ago by remvanthull
  2

• Can you provide a download link for the pth file of the SAM model?

  #47 opened 6 months ago by MenSanYan
  3

• token_positives

  #53 opened 6 months ago by Pumpkin123709
  2

• assertion error cur_len == total_len

  #54 opened 6 months ago by bibibabibo26
  1

• Empty output when inferring on the example image.

  #34 opened 6 months ago by JianqiangWan
  0

• Question about Output Quality Difference Between Local and Online Demo for MBZUAI/GLaMM-FullScope

  #39 opened 6 months ago by Jayce1kk
  3

• Fine-tuning Grounded Conversation Generation (GCG) Task

  #52 opened 7 months ago by hungnh1125
  4

• Some bugs in the GranD_ReferringSegm_ds.py

  #50 opened 7 months ago by xandery-geek
  0

• may i ask your total parameter?

  #49 opened 7 months ago by CoderZhangYx
  0

• local llm interface for glamm

  #44 opened 8 months ago by whpy
  1

• Running GranD Automated Annotation pipeline from scratch

  #43 opened 8 months ago by sankalpsinha-cmos
  1

• Fluctuate results on RefCOCO Family when evaluating the referring expression segmentation.

  #42 opened 8 months ago by Glupayy
  1

• An error is reported when running eval

  #41 opened 8 months ago by clevercaicai
  5

• GrandD Detailed Operation Guide

  #35 opened 9 months ago by hzdzkjdxyjs
  7

• Release of pre-training instructions?

  #31 opened 9 months ago by remvanthull
  9

• Grand-env

  #36 opened 9 months ago by hzdzkjdxyjs
  2

• A bug in region captioning evaluation scripts

  #40 opened 9 months ago by machuofan
  1

• About GranD Pre-training Dataset

  #37 opened 9 months ago by Shengcao-Cao
  2

• the demo caption is very simple

  #38 opened 9 months ago by trouble-maker007
  1

• GLaMM-FullScope model generates only a single mask

  #32 opened 10 months ago by preddy5
  2

• Undefined `self.base_dir` in `GranDfDataset.__init__`

  #30 opened 10 months ago by function2-llx
  1

• Phrase grounding model

  #29 opened 10 months ago by ekazakos
  0