yformer/EfficientSAM

Issues

• Fine-tunning the original model to new tasks with few-shot adaption

  #78 opened 2 months ago by NTUZZH
  0

• how to train our dataset？thanks for your answer

  #55 opened a year ago by wyk-study
  3

• When there are multiple points as prompts (for example, more than five points), some point areas cannot be segmented.

  #65 opened a year ago by daeing
  2

• torch.onnx.errors.UnsupportedOperatorError: Exporting the operator 'aten::tile' to ONNX opset version 17 is not supported.

  #47 opened a year ago by xwhkkk
  4

• SqueezeSAM

  #51 opened a year ago by jrhe
  3

• how to use background point

  #64 opened a year ago by KingerFzb
  4

• how to ensure the iou prediction between zero and one?

  #77 opened 7 months ago by Altria7
  1

• pre-trained parameters

  #68 opened a year ago by Yy4441867
  1

• Feature extraction of image encoder

  #76 opened 7 months ago by CurryKd7
  1

• Why is it slow to segment everything？ Is there a good solution？

  #69 opened a year ago by shuaifengj
  7

• Why is it running slow and segment-anything is not giving good results?

  #75 opened 7 months ago by daytoy01
  1

• Will you integrate with SAM2?

  #74 opened 7 months ago by CoderZhangYx
  1

• What does input_labels mean?

  #61 opened a year ago by nightwindnohen
  2

• the efficientSAM model do not support input bounding box-prompt?

  #40 opened 8 months ago by duxuan11
  1

• pre-training code and fine-tuning code

  #73 opened 9 months ago by fhw0824
  0

• eval on COCO dataset

  #38 opened a year ago by shawnricecake
  3

• multibox-prompt inference

  #62 opened a year ago by BeliverK
  2

• Wrong EfficientSAM model from Model_zoo

  #72 opened 10 months ago by yang-fei
  0

• RuntimeError: expected scalar type float but found double

  #37 opened a year ago by TaoTXiXi
  6

• SAMI Module and Training Codes?

  #56 opened a year ago by BingoNate
  4

• what is the minimum memory required for the GPU

  #41 opened a year ago by ghm666
  1

• Is it possible to fine-tune it to extract single-category objects based only on mask prompt

  #70 opened a year ago by 1248493632
  0

• Is there GPU support for box-prompted SAM?

  #58 opened a year ago by silinsi
  7

• pre-trained parameters

  #67 opened a year ago by Yy4441867
  0

• Saliency Segment CODE WANTED

  #54 opened a year ago by happyfox-dot
  3

• CoreML

  #52 opened a year ago by FerusAndBeyond
  2

• Is that possible using this as pretrained with LLaVa?>

  #60 opened a year ago by lucasjinreal
  4

• Using SAM original prompt encoder with EfficientSAM

  #48 opened a year ago by carlosuc3m
  2

• The output mask with different information granularity

  #50 opened a year ago by xwhkkk
  1

• How to do Saliency segmentation?

  #53 opened a year ago by xinli2008
  1

• Segment Anything CPP Wrapper for macOS

  #57 opened a year ago by ryouchinsa
  1

• why zero-shot instance segmentation on COCO dataset is bad

  #59 opened a year ago by liuxy1103
  1

• EfficientSAM available on the Microscopy Imaging software Fiji

  #63 opened a year ago by carlosuc3m
  1

• "segment-anything" is slow

  #35 opened a year ago by GitChanyoung
  6

• What does input label mean in code?

  #39 opened a year ago by ghm666
  2

• Why is the decoder_max_num_input_points set to 6

  #49 opened a year ago by Doctor-Damu
  0

• Expected data type and value range of the input images

  #44 opened a year ago by carlosuc3m
  2

• Confusion about the pre-training cross-attention's K and V

  #46 opened a year ago by wangbxj1234
  0

• different in jit to pt model

  #42 opened a year ago by Whatsetsthisend
  3

• Regarding the issue of EfficientSAM of checkpoints

  #36 opened a year ago by feivellau
  5

• Expose `multimask_output` in `EfficientSam.forward`

  #30 opened a year ago by MichaelFishmanBDAII
  3

• Code about Cross-Attention Decoder

  #33 opened a year ago by 123456789asdfjkl
  2

• will release the pretraining code?

  #31 opened a year ago by Yut-tuat
  2

• Regarding the performance of SqueezeSAM

  #34 opened a year ago by xiankgx
  1

• How to use a text prompt.

  #26 opened a year ago by GitChanyoung
  3

• Finetuning for downstream segmentation task

  #32 opened a year ago by agraham9966
  2

• after load jit file, torchscript runtimeError

  #24 opened a year ago by dreaming12580
  1

• The output mask is 3*w*h. I need to take the masked channel as the result. Or should I merge these channels?

  #28 opened a year ago by loorr
  2

• The inference time significantly increases when using multi-point prompts.

  #29 opened a year ago by EmptyCity1995
  0

• OutOfMemoryError

  #25 opened a year ago by ccy610
  5