yformer/EfficientSAM issues and pull requests

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

Issue - State: open - Opened by NTUZZH 10 days ago

#77 - how to ensure the iou prediction between zero and one?

Issue - State: open - Opened by Altria7 5 months ago - 1 comment

#76 - Feature extraction of image encoder

Issue - State: open - Opened by CurryKd7 5 months ago - 1 comment

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

Issue - State: open - Opened by daytoy01 5 months ago - 1 comment

#74 - Will you integrate with SAM2?

Issue - State: open - Opened by CoderZhangYx 5 months ago - 1 comment

#73 - pre-training code and fine-tuning code

Issue - State: open - Opened by fhw0824 7 months ago

#72 - Wrong EfficientSAM model from Model_zoo

Issue - State: open - Opened by yang-fei 8 months ago

#71 - Add fine-tuning result to main

Pull Request - State: closed - Opened by Andy-LZH 8 months ago

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

Issue - State: open - Opened by 1248493632 9 months ago

#69 - Why is it slow to segment everything？ Is there a good solution？

Issue - State: open - Opened by shuaifengj 10 months ago - 7 comments

#68 - pre-trained parameters

Issue - State: open - Opened by Yy4441867 10 months ago - 1 comment

#67 - pre-trained parameters

Issue - State: closed - Opened by Yy4441867 10 months ago

#66 - ONNX export does not work with Segment Everything

Pull Request - State: open - Opened by kdubovikov 10 months ago

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

Issue - State: open - Opened by daeing 10 months ago - 2 comments

#64 - how to use background point

Issue - State: open - Opened by KingerFzb 10 months ago - 4 comments

#63 - EfficientSAM available on the Microscopy Imaging software Fiji

Issue - State: open - Opened by carlosuc3m 11 months ago - 1 comment

#62 - multibox-prompt inference

Issue - State: open - Opened by BeliverK 11 months ago - 2 comments

#61 - What does input_labels mean?

Issue - State: open - Opened by nightwindnohen 11 months ago - 2 comments

#60 - Is that possible using this as pretrained with LLaVa?>

Issue - State: open - Opened by lucasjinreal 11 months ago - 4 comments

#59 - why zero-shot instance segmentation on COCO dataset is bad

Issue - State: open - Opened by liuxy1103 11 months ago - 1 comment

#58 - Is there GPU support for box-prompted SAM?

Issue - State: open - Opened by silinsi 11 months ago - 7 comments

#57 - Segment Anything CPP Wrapper for macOS

Issue - State: open - Opened by ryouchinsa 11 months ago - 1 comment

#56 - SAMI Module and Training Codes?

Issue - State: open - Opened by BingoNate 11 months ago - 4 comments

#55 - how to train our dataset？thanks for your answer

Issue - State: open - Opened by wyk-study 11 months ago - 3 comments

#54 - Saliency Segment CODE WANTED

Issue - State: open - Opened by happyfox-dot 11 months ago - 3 comments

#53 - How to do Saliency segmentation?

Issue - State: open - Opened by xinli2008 11 months ago - 1 comment

#52 - CoreML

Issue - State: closed - Opened by FerusAndBeyond 11 months ago - 2 comments

#51 - SqueezeSAM

Issue - State: open - Opened by jrhe 11 months ago - 3 comments

#50 - The output mask with different information granularity

Issue - State: open - Opened by xwhkkk 12 months ago - 1 comment

#49 - Why is the decoder_max_num_input_points set to 6

Issue - State: open - Opened by Doctor-Damu 12 months ago

#48 - Using SAM original prompt encoder with EfficientSAM

Issue - State: open - Opened by carlosuc3m 12 months ago - 2 comments

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

Issue - State: open - Opened by xwhkkk 12 months ago - 4 comments

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

Issue - State: open - Opened by wangbxj1234 about 1 year ago

#45 - Add Hugging Face integration

Pull Request - State: open - Opened by NielsRogge about 1 year ago - 4 comments

#44 - Expected data type and value range of the input images

Issue - State: closed - Opened by carlosuc3m about 1 year ago - 2 comments

#43 - move to cuda & small fixes

Pull Request - State: open - Opened by Skwarson96 about 1 year ago - 1 comment

#42 - different in jit to pt model

Issue - State: closed - Opened by Whatsetsthisend about 1 year ago - 3 comments

#41 - what is the minimum memory required for the GPU

Issue - State: open - Opened by ghm666 about 1 year ago - 1 comment

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

Issue - State: closed - Opened by duxuan11 about 1 year ago - 1 comment

#39 - What does input label mean in code?

Issue - State: closed - Opened by ghm666 about 1 year ago - 2 comments

#38 - eval on COCO dataset

Issue - State: open - Opened by shawnricecake about 1 year ago - 3 comments

#37 - RuntimeError: expected scalar type float but found double

Issue - State: open - Opened by TaoTXiXi about 1 year ago - 6 comments

#36 - Regarding the issue of EfficientSAM of checkpoints

Issue - State: open - Opened by feivellau about 1 year ago - 5 comments

#35 - "segment-anything" is slow

Issue - State: open - Opened by GitChanyoung about 1 year ago - 6 comments

#34 - Regarding the performance of SqueezeSAM

Issue - State: closed - Opened by xiankgx about 1 year ago - 1 comment

#33 - Code about Cross-Attention Decoder

Issue - State: open - Opened by 123456789asdfjkl about 1 year ago - 2 comments

#32 - Finetuning for downstream segmentation task

Issue - State: open - Opened by agraham9966 about 1 year ago - 2 comments

#31 - will release the pretraining code?

Issue - State: open - Opened by Yut-tuat about 1 year ago - 2 comments

#30 - Expose `multimask_output` in `EfficientSam.forward`

Issue - State: open - Opened by MichaelFishmanBDAII about 1 year ago - 3 comments

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

Issue - State: closed - Opened by EmptyCity1995 about 1 year ago

#28 - The output mask is 3wh. I need to take the masked channel as the result. Or should I merge these channels?

Issue - State: closed - Opened by loorr about 1 year ago - 2 comments

#27 - Update EfficientSAM_example.ipynb for SqueezeSAM

Pull Request - State: closed - Opened by JayyShah about 1 year ago

#26 - How to use a text prompt.

Issue - State: open - Opened by GitChanyoung about 1 year ago - 3 comments

#25 - OutOfMemoryError

Issue - State: closed - Opened by ccy610 about 1 year ago - 5 comments

#24 - after load jit file, torchscript runtimeError

Issue - State: closed - Opened by dreaming12580 about 1 year ago - 1 comment

#23 - Datasets used in pretraining

Issue - State: open - Opened by Cbtor about 1 year ago - 1 comment

#22 - Update EfficientSAM_example.ipynb

Pull Request - State: closed - Opened by SeaOtocinclus about 1 year ago - 2 comments

#21 - How do you generate masked tokens?

Issue - State: closed - Opened by lianjinke about 1 year ago - 6 comments

#20 - OutOfMemoryError

Issue - State: closed - Opened by ccy610 about 1 year ago

#19 - Integration to segment_anything package?

Issue - State: open - Opened by oranshayer about 1 year ago - 5 comments

#18 - Update EfficientSAM_example.ipynb

Pull Request - State: closed - Opened by eltociear about 1 year ago - 1 comment

#17 - Efficient SAM has no response to negative point prompt

Issue - State: open - Opened by summelon about 1 year ago - 2 comments

#16 - Title: Query on EfficientSAM's Adaptability for Low-Resource Environments

Issue - State: open - Opened by yihong1120 about 1 year ago - 8 comments

#15 - grounded-efficient-sam demo support

Issue - State: open - Opened by rentainhe about 1 year ago - 3 comments

#14 - What are bounding box labels for?

Issue - State: closed - Opened by colinator about 1 year ago - 2 comments

#13 - Multiple run-time errors

Issue - State: closed - Opened by colinator about 1 year ago - 5 comments

#12 - will release the training code?

Issue - State: open - Opened by zimenglan-sysu-512 about 1 year ago - 3 comments

#11 - Multi-bbox inference

Issue - State: open - Opened by sulaimanvesal about 1 year ago - 12 comments

#10 - Regression from original

Issue - State: closed - Opened by Chris-toe-pher about 1 year ago - 5 comments

#9 - Failed to export model to ONNX

Issue - State: closed - Opened by ArielleBF about 1 year ago - 14 comments

#8 - [fix] fix example ipynb runtime error

Pull Request - State: closed - Opened by SoTosorrow about 1 year ago - 1 comment

#7 - Consider hosting model files in repo itself

Issue - State: closed - Opened by srinify about 1 year ago - 3 comments

#6 - NameError: name 'img_tensor' is not defined

Issue - State: closed - Opened by MuhammadBilal848 about 1 year ago - 2 comments

#5 - How to inspect the intermediate output of the model?

Issue - State: closed - Opened by MrPeterJin about 1 year ago - 4 comments

#4 - models for other devices

Issue - State: closed - Opened by AmitIsraeli about 1 year ago - 2 comments

#3 - Pre-trained models

Issue - State: open - Opened by wondervictor about 1 year ago - 1 comment

#2 - fixed a misspelled word in readme

Pull Request - State: closed - Opened by spacewalk01 about 1 year ago - 1 comment

#1 - How to perform "segment everything" and "salient instance segmentation"??

Issue - State: open - Opened by xiankgx about 1 year ago - 16 comments

GitHub / yformer/EfficientSAM issues and pull requests