SysCV/sam-hq

Issues

• How to train vit_tiny (Light HQ-SAM for real-time need): ViT-Tiny HQ-SAM model?

  #130 opened 8 months ago by Andy718811
  2

• no such pth file

  #137 opened 6 months ago by hz-1
  1

• Does SAM_HQ support batch input?

  #135 opened 7 months ago by yunniw2001
  1

• Question about HQ-Output Token and weight updates in the frozen Mask Decoder

  #145 opened 3 months ago by Linn0910
  0

• Train Light HQ-SAM

  #144 opened 3 months ago by bobo59
  0

• Request for evaluation code

  #113 opened a year ago by jameslahm
  6

• Transform samhq into tensorrt!

  #143 opened 4 months ago by zhujiajian98
  0

• About the console output during validation.

  #142 opened 4 months ago by FolkScientistInDL
  1

• Input mask prompt

  #141 opened 4 months ago by theFilipko
  0

• The val_iou and val_boundary_iou is very low

  #107 opened a year ago by Ghy1209
  1

• High-level question: is SAM-HQ suited for fine-tuning on specific tasks?

  #140 opened 5 months ago by SimonCoste
  2

• Evaluation for instance segmentation

  #139 opened 6 months ago by wliu20
  0

• RuntimeError

  #138 opened 6 months ago by hz-1
  0

• Positive negative point inputs for SAM-hq

  #136 opened 7 months ago by varadtechx
  0

• Can we add support for transformers?

  #122 opened a year ago by moneyhotspring
  3

• Alternative implementation in Refiners

  #127 opened 7 months ago by hugojarkoff
  0

• About the issue of positive and negative sample pairs

  #134 opened 8 months ago by leinusi
  1

• can't we get candidates as original sam?

  #133 opened 8 months ago by TikaToka
  0

• Visualization of Figure 6

  #132 opened 8 months ago by tqinger
  0

• Why can't we achieve the demonstration effect? There are three tennis rackets in the incoming image, and only one mask is returned

  #131 opened 8 months ago by hjj-lmx
  0

• Runtime error in Colab

  #129 opened 8 months ago by gttae
  1

• About interm_embeddings

  #128 opened 8 months ago by zzzyzh
  0

• Can sam-hq perform breakpoint training: continue training on the already trained sam-hq, or continue training on the official sam-hq weights

  #126 opened 9 months ago by YUANMU227
  2

• Segment Anything CPP Wrapper for macOS

  #125 opened 9 months ago by ryouchinsa
  0

• Training problem: During the training of sam-hq, the iou output of the val set is very high, 0.98; but in eval mode, the iou of the val set is only 0.48

  #124 opened 10 months ago by YUANMU227
  0

• Will a fast version be released like segment-anything-fast?

  #112 opened a year ago by yatengLG
  3

• RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 1 but got size 13 for tensor number 1 in the list.

  #123 opened a year ago by stevezkw1998
  1

• RuntimeError: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW

  #121 opened a year ago by stevezkw1998
  0

• Question about Ablation study

  #120 opened a year ago by mcshih
  4

• Can I have a more specific using example (code snippet) in README.md?

  #119 opened a year ago by stevezkw1998
  5

• About obtaining uvo data set ap or boundary ap

  #114 opened a year ago by yaohusama
  5

• The purpose of self.embedding_maskfeature

  #117 opened a year ago by thanhdh-3030
  3

• About the number of detect boxes

  #118 opened a year ago by yaohusama
  2

• How can I test the model

  #116 opened a year ago by Ryanye2000
  1

• When i tried to train the mode. There is a bug

  #100 opened a year ago by Ryanye2000
  6

• The ap of lvis measured by the public model is inconsistent with the ap in the paper.

  #115 opened a year ago by yaohusama
  1

• Question: Is it SAM-HQ model applicable for predicting segmentation mask for the input images without boxes, point or label?

  #106 opened a year ago by mzg0108
  2

• Multi-box input To use multi-box prompt inputs

  #108 opened a year ago by yliuosu
  1

• error in 'demo_hqsam_automatic_mask_generator.ipynb'

  #111 opened a year ago by Kyle-RuidongLI
  0

• dcm file input questions

  #110 opened a year ago by Ryanye2000
  0

• dcm file imput

  #109 opened a year ago by Ryanye2000
  0

• some questions about training SAM_HQ

  #105 opened a year ago by Ghy1209
  2

• Tuning Segment for clothing

  #104 opened a year ago by crapthings
  0

• when i run train.py with one gpu and dataset that sam_hq used, the process stopped and didn't move

  #103 opened a year ago by Ryanye2000
  5

• Grounded HQ-SAM

  #101 opened a year ago by halqadasi
  1

• Has anyone attempted to deploy SAM-Hq on CVAT (following the deployment of SAM)

  #102 opened a year ago by superNCS
  0

• I want to ask if there is a way that i give the tif image and bbox label as my dataset

  #99 opened a year ago by Ryanye2000
  1

• the code of Light HQ-SAM vs MobileSAM on COCO using the FocalNet-DINO

  #98 opened a year ago by Ghy1209
  0

• May i ask if there is a way to use dcm image to train the model? If its available, what should i do.

  #97 opened a year ago by Ryanye2000
  2

• Text Prompt

  #96 opened a year ago by sebastianopazo1
  1