hkchengrex/Tracking-Anything-with-DEVA issues and pull requests

#113 - Can you provide detailed testing code and instructions for YouTubeVIS

Issue - State: closed - Opened by longmalongma about 2 months ago - 1 comment

#100 - Cannot segment and track Gundam. Any suggestion? Thanks

Issue - State: closed - Opened by garrisonz 5 months ago - 1 comment

#99 - How to Perform Inference on Multiple Videos?

Issue - State: closed - Opened by weilllllls 5 months ago - 1 comment

#98 - Floor tracking is poor. Any suggestion?

Issue - State: closed - Opened by garrisonz 5 months ago - 3 comments

#97 - RuntimeError: shape '[1, 63, 512, 20, 27]' is invalid for input of size 19353600

Issue - State: closed - Opened by GuanghaoJin 5 months ago - 2 comments

#96 - Will changing the batch size from 16 to 18 and running with 6 cards result in performance loss?

Issue - State: closed - Opened by longmalongma 6 months ago - 3 comments

#95 - Support HQ-SAM in text-prompt mode with Grounding DINO

Pull Request - State: closed - Opened by lkeab 6 months ago - 1 comment

#94 - reading data is particularly slow

Issue - State: closed - Opened by longmalongma 6 months ago - 2 comments

#93 - Hello, I found that this method matches black results when there are only two images of this input.。。

Issue - State: open - Opened by chenkangjie1123 6 months ago - 1 comment

#92 - Can deva be extended to video semantic segmentation and video instance segmentation tasks?

Issue - State: closed - Opened by longmalongma 6 months ago - 4 comments

#91 - Subsampling BURST when evaluating

Issue - State: closed - Opened by chhchan 6 months ago - 1 comment

#90 - RuntimeWarning: Trying to segment without any memory

Issue - State: closed - Opened by Masrur02 6 months ago - 10 comments

#89 - SAM for the training sets of YouTube VOS and Davis 2017

Issue - State: closed - Opened by longmalongma 6 months ago - 2 comments

#88 - Something about the provided detection on VIPSeg

Issue - State: closed - Opened by chhchan 6 months ago - 3 comments

#87 - The mask in example

Issue - State: closed - Opened by wkywwds 6 months ago - 3 comments

#86 - How to get subpart/part/whole-level segmentation like SAM？

Issue - State: closed - Opened by chenkangjie1123 6 months ago - 4 comments

#85 - something about data format

Issue - State: open - Opened by wkywwds 7 months ago - 29 comments

#84 - RuntimeWarning: Trying to segment without any memory!

Issue - State: closed - Opened by Masrur02 7 months ago - 7 comments

#83 - extracting mask and bbox

Issue - State: closed - Opened by shani1610 7 months ago - 1 comment

#82 - Just want to confirm!

Issue - State: closed - Opened by JawadTawhidi 7 months ago - 1 comment

#81 - Just want to confirm!

Issue - State: closed - Opened by JawadTawhidi 7 months ago - 5 comments

#80 - Parameter Adjustment in Automatic Mode and Objects Reappearance Problem

Issue - State: closed - Opened by dhgras 7 months ago - 2 comments

#79 - U-net with DEVA

Issue - State: closed - Opened by wkywwds 7 months ago - 13 comments

#78 - yolo_world with DEVA

Issue - State: closed - Opened by LLH-Harward 7 months ago - 2 comments

#77 - TrustImageSeg Inference

Issue - State: closed - Opened by SangbeomLim 7 months ago - 1 comment

#76 - 0-5 represents the target?

Issue - State: closed - Opened by longmalongma 8 months ago - 4 comments

#75 - Didn't you use a mask that was inferred from a large model during semi-youtubevos inference?

Issue - State: closed - Opened by longmalongma 8 months ago - 3 comments

#74 - target tracking count

Issue - State: closed - Opened by YuqiuDeng 8 months ago - 1 comment

#73 - How do I reproduce the results of the rvos report？

Issue - State: open - Opened by xinbaiw 8 months ago - 11 comments

#72 - how to get the mask path to detections for rvos

Issue - State: closed - Opened by xinbaiw 8 months ago - 2 comments

#71 - replaced deprecated BoxAnnotator with BoundingBoxAnnotator and LabelA…

Pull Request - State: closed - Opened by husejinbg 8 months ago - 1 comment

#70 - valueerror of text prompt

Issue - State: closed - Opened by shangchengPKU 8 months ago - 2 comments

#69 - text prompt

Issue - State: closed - Opened by yangyang117 8 months ago - 1 comment

#68 - High Memory Usage During Initialization

Issue - State: open - Opened by kaankarakose 8 months ago - 2 comments

#67 - Error in the middle of a video.

Issue - State: closed - Opened by Mountchicken 8 months ago - 2 comments

#66 - Replace [grounding-dino+sam] with [yolo-world+efficient-sam]

Issue - State: closed - Opened by guoqincode 8 months ago - 1 comment

#65 - Using DEVA with a different mask model causing issues with mask encoding

Issue - State: closed - Opened by vineetparikh 8 months ago - 3 comments

#64 - Wrong segmentation appears after several objects come and go from the scene

Issue - State: closed - Opened by be-hd 8 months ago - 6 comments

#63 - Segmentation broken after 20 seconds or when total about more than 30 objects appeared in the video

Issue - State: closed - Opened by huyen-do-helm 8 months ago - 1 comment

#62 - Crop / segment the objects

Issue - State: closed - Opened by tralala87 9 months ago - 1 comment

#61 - Deva on CPU

Issue - State: closed - Opened by riccardo24-7 9 months ago - 1 comment

#60 - Licence

Issue - State: closed - Opened by makemate 10 months ago - 1 comment

#59 - How to inference a video directly

Issue - State: closed - Opened by wuyiqii 10 months ago - 2 comments

#58 - Is there a way to use DEVA with Cutie?

Issue - State: closed - Opened by goneflash 10 months ago - 3 comments

#57 - None in category_ids

Issue - State: closed - Opened by Bariona 10 months ago - 2 comments

#56 - Pre-trained model

Issue - State: closed - Opened by cwt000297 10 months ago - 1 comment

#55 - Deva run out of memory with "Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use."

Issue - State: closed - Opened by zhangzehao123 10 months ago - 1 comment

#54 - Deva out of memory

Issue - State: closed - Opened by zhangzehao123 10 months ago - 3 comments

#53 - Not working if there is large variation between consecutive frames??

Issue - State: closed - Opened by JawadTawhidi 11 months ago - 5 comments

#52 - Is it normal for DEVA's training speed to be much slower than XMem?

Issue - State: closed - Opened by longmalongma 11 months ago - 5 comments

#51 - Why is the training speed of DEVA much slower than XMem?

Issue - State: closed - Opened by longmalongma 11 months ago - 3 comments

#50 - About training details

Issue - State: closed - Opened by csustYyh 11 months ago - 1 comment

#49 - Can your method be applied to other video segmentation tasks?

Issue - State: closed - Opened by longmalongma 11 months ago - 1 comment

#48 - Train error

Issue - State: closed - Opened by KnSun99 12 months ago - 14 comments

#47 - Is ovis used for training networks? Do you have a download link？

Issue - State: closed - Opened by longmalongma 12 months ago - 5 comments

#46 - Unexpected segmentation output

Issue - State: closed - Opened by JawadTawhidi 12 months ago - 7 comments

#45 - Error while inference

Issue - State: closed - Opened by JawadTawhidi 12 months ago - 14 comments

#44 - Have you made all the code public?

Issue - State: closed - Opened by longmalongma 12 months ago - 1 comment

#43 - Installation issue

Issue - State: closed - Opened by JawadTawhidi 12 months ago - 6 comments

#42 - Error while calculating J&F value

Issue - State: closed - Opened by JawadTawhidi 12 months ago - 2 comments

#41 - Question regarding inference

Issue - State: closed - Opened by JawadTawhidi 12 months ago - 7 comments

#40 - How many large memory machines do you need for training?

Issue - State: closed - Opened by longmalongma 12 months ago - 2 comments

#39 - new video test on pretrained model

Issue - State: closed - Opened by doublemanyu 12 months ago - 1 comment

#38 - Can I use it for ultrasound video object segmentation?

Issue - State: closed - Opened by JawadTawhidi about 1 year ago - 7 comments

#37 - Advice on optimizing use?

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

#36 - uvos

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

#35 - Running on macos / mps

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

#34 - fine-tune static image for medical domain

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

#33 - How to reproduce VIP-Seg results

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

#32 - NameError: name '_C' is not defined

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

#31 - Extract the ROI of the masked regions

Issue - State: closed - Opened by vanamagautam24 about 1 year ago - 3 comments

#30 - VRAM needed

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

#29 - What is the minimum amount of video memory required for a graphics card?

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

#28 - box not right in multi-person scenes

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

#27 - Using Postive and negative points for each object as prompts

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

#26 - How to train my own dataset?

Issue - State: closed - Opened by AK51 about 1 year ago - 1 comment

#25 - Video does not have browser-compatible container or codec. Converting to mp4?

Issue - State: closed - Opened by AK51 about 1 year ago - 2 comments

#24 - Problem installing Grounded-Segment-Anything with Cuda 12.2

Issue - State: closed - Opened by AK51 about 1 year ago - 2 comments

#23 - cannot read the pth file?

Issue - State: closed - Opened by Lanson426 about 1 year ago - 1 comment

#22 - Some confusion about Table S1

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

#21 - ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 1293) of binary

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

#20 - installing on WSL2

Issue - State: closed - Opened by 21pl about 1 year ago - 2 comments

#19 - Insufficient GPU memory

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

#18 - Installation Guide for SAM and Grounding DINO

Pull Request - State: open - Opened by PrashantDixit0 about 1 year ago - 2 comments

#17 - how can I enable cpu to run the demo_gradio.py

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

#16 - Missing frames

Issue - State: closed - Opened by jhwang7628 about 1 year ago - 2 comments

#15 - CUDA_HOME

Issue - State: closed - Opened by 21pl about 1 year ago - 2 comments

GitHub / hkchengrex/Tracking-Anything-with-DEVA issues and pull requests