UX-Decoder/Segment-Everything-Everywhere-All-At-Once issues and pull requests

#154 - Using prompts

Issue - State: open - Opened by benakhovan32561 17 days ago

#153 - Difference between SEEM and X-decoder

Issue - State: open - Opened by zhi-xuan-chen 22 days ago

#152 - How can I run inference referring image task on my local

Issue - State: open - Opened by mkoursha about 1 month ago

#151 - I have such a problem and hope to get your help，Running app.py will display the web page, but uploading the image does not output the results of the model, which bothers me

Issue - State: open - Opened by HaoranKong 2 months ago - 1 comment

#150 - .arrow files fr training

Issue - State: open - Opened by IceBubble217 3 months ago

#149 - Deformable Attention weights

Issue - State: open - Opened by david-rohrschneider 3 months ago

#148 - Demo URL not accessible

Issue - State: open - Opened by moehmeni 3 months ago - 1 comment

#147 - If there are multiple objects in the image, why is only one selected?

Issue - State: closed - Opened by Note-Liu 3 months ago

#146 - ModuleNotFoundError: No module named 'modeling'

Issue - State: closed - Opened by Note-Liu 3 months ago - 2 comments

#145 - AttributeError: 'GeneralizedSEEM' object has no attribute 'evaluate_demo'

Issue - State: closed - Opened by wtmshanbao 4 months ago - 1 comment

#144 - the mask in image and ref_img

Issue - State: open - Opened by XiaokunFeng 4 months ago

#143 - inference demo of ref_img setting

Issue - State: closed - Opened by XiaokunFeng 4 months ago - 2 comments

#142 - Ask about using SEEM with SA3D

Issue - State: closed - Opened by mw-JHC 4 months ago - 1 comment

#141 - Does the dmoe website support TIFF image format?

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

#140 - How to train your own dataset

Issue - State: open - Opened by biyuefeng 5 months ago - 5 comments

#139 - This is working

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

#138 - Config Issue - Load pretrained sam_vit_l_0b3195.pth

Issue - State: closed - Opened by dongho-Han 6 months ago

#137 - GPU Out of Memory Issue

Issue - State: open - Opened by dongho-Han 6 months ago - 6 comments

#136 - How to change the size of the training set?

Issue - State: open - Opened by EricZavier 6 months ago

#135 - The demo website can't be accessed

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

#134 - ValueError: Unknown scheme for proxy URL URL('socks://localhost:10808/')

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

#133 - When I was running "pip install -r assets/requirements/requirements.txt", I got the following errors. Could you please tell me what should I do?

Issue - State: closed - Opened by AImagicAI 6 months ago - 5 comments

#132 - Bug when getting the neg_mask

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

#131 - The demo website can't be accessed

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

#130 - What is the relationship with Semantic-SAM?

Issue - State: closed - Opened by kexul 7 months ago

#129 - Package

Pull Request - State: closed - Opened by Wenjun-Ji 7 months ago

#128 - Local inference for an image given point prompt coordinates

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

#127 - Scripts for Interactive Validation on COCO

Issue - State: open - Opened by tjqual 7 months ago - 4 comments

#126 - what does `grounding_hash ` mean?

Issue - State: open - Opened by xianshunw 7 months ago - 1 comment

#125 - Multi-gpu training

Issue - State: open - Opened by Jinjun58 7 months ago - 1 comment

#124 - Multi-object interaction support

Issue - State: open - Opened by asif07hossain 7 months ago

#123 - How to build caption_class_similarity.pth?

Issue - State: open - Opened by Lewislou 8 months ago

#122 - bbox prediction

Issue - State: open - Opened by msdkarimi 8 months ago

#121 - Support for video segmentation demo without referring image

Issue - State: open - Opened by mukulkhanna 8 months ago - 1 comment

#120 - Actual batch size with multiple GPUs

Issue - State: open - Opened by IceBubble217 8 months ago

#119 - The results of online and local demos are inconsistent.

Issue - State: open - Opened by becauseofAI 9 months ago - 1 comment

#118 - Semantic segmentation GT file

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

#117 - 2 problems happened when I used entry.py for evaluate

Issue - State: open - Opened by xpzwzwz 9 months ago - 2 comments

#115 - the demo in the project seems to be inaccessible

Issue - State: open - Opened by studentyyh 9 months ago - 4 comments

#114 - SEEM, validation

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

#113 - Fine-tunning model on instance segmentation tasks without prompts

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

#112 - Training Time Estimation

Issue - State: open - Opened by ziqipang 9 months ago - 3 comments

#111 - Question about the dataset.

Issue - State: open - Opened by Rexzhan 9 months ago - 8 comments

#110 - Question about match id.

Issue - State: open - Opened by CrazyLenmon 9 months ago - 1 comment

#109 - Update README.md

Pull Request - State: open - Opened by wang-kexian 9 months ago

#108 - Trying to Run it locally on my system but unable to Succeed

Issue - State: open - Opened by mudasar10147 9 months ago - 1 comment

#107 - During the evaluation phase, a warning error occurred stating that only support batch size equal to 1

Issue - State: open - Opened by EricZavier 9 months ago - 8 comments

#106 - Demo link is not working / seems broken

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

#105 - Can I conduct distributed experimental training on eight GPUs on two servers?

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

#104 - Is there a test script? What do I do if I want to mass predict a photo set?

Issue - State: open - Opened by lizhiwen19900709 10 months ago - 1 comment

#103 - TypeError: object of type 'AspectRatioGroupedDataset' has no len()

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

#102 - TypeError: object of type 'AspectRatioGroupedDataset' has no len()

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

#101 - Package branch errors

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

#100 - Update distributed.py

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

#99 - CUDA version mismatch between X-Decoder and Detectron2

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

#98 - Errors occurred when installing the requirements.txt

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

#97 - RefCOCOg Results

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

#96 - medical images

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

#95 - Extract feature？

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

#94 - both visual and textual prompts demo?

Issue - State: closed - Opened by zgyh001 10 months ago - 2 comments

#93 - There are unclosed tags in the XML file

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

#92 - Can it be trained or fine-tuned on custom datasets?

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

#91 - c++

Issue - State: closed - Opened by xiangw369 10 months ago - 1 comment

#90 - SEEM in remote sensing images segmantation task.

Issue - State: closed - Opened by Aki-Tomoya 11 months ago - 6 comments

#89 - How to address the issue of objects mentioned in the prompt not appearing in the target image?

Issue - State: closed - Opened by Ian990466 11 months ago - 3 comments

#88 - Inference in local instead of the http demo？

Issue - State: open - Opened by Feobi1999 11 months ago - 2 comments

#87 - Training with Alternative Datasets

Issue - State: closed - Opened by IceBubble217 11 months ago

#86 - Eval duration

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

#85 - ModuleNotFoundError: No module named 'caption_pycocotools'

Issue - State: closed - Opened by lizhiwen19900709 11 months ago - 15 comments

#84 - OSError: Can't load tokenizer for 'openai/clip-vit-base-patch32'

Issue - State: open - Opened by lizhiwen19900709 11 months ago - 1 comment

#83 - Error when running training script

Issue - State: closed - Opened by IceBubble217 11 months ago - 6 comments

#82 - How can I use it for video track?

Issue - State: open - Opened by lfy523 11 months ago - 1 comment

#81 - Multiple Interactive object inference demo example

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

#80 - Training set for the gradio demo

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

#79 - Training encountered a problem

Issue - State: closed - Opened by ddddkk 12 months ago - 3 comments

#78 - Failure to find all objects in text prompt mode

Issue - State: closed - Opened by xiaobanni 12 months ago - 4 comments

#77 - SOTA Model for Text Prompt Segmentation

Issue - State: closed - Opened by xiaobanni 12 months ago - 4 comments

#76 - Gradio: Expecting value: line 2 column 1 (char 1)

Issue - State: closed - Opened by ouyanglinke 12 months ago

#75 - Huggingface demo not working

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

#74 - Request for Training Code Release Timeline

Issue - State: closed - Opened by zhangnanyue almost 1 year ago - 4 comments

#73 - When will the training code be released

Issue - State: closed - Opened by songyang86 almost 1 year ago - 1 comment

#72 - How to implement video splitting in the demo version

Issue - State: closed - Opened by cricket-111 about 1 year ago - 1 comment

#71 - interactive mode

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

#70 - When will the training code be released

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

#69 - How to handle training data containing only a single type of interaction?

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

#68 - SEEM-Tiny Checkpoint download permissions issue

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

#67 - Understanding the logits

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

#66 - How to refine the seg result?

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

#65 - Demo is down

Issue - State: closed - Opened by Jonas1312 about 1 year ago - 2 comments

#64 - How to get better results for open-set segmentation?

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

#63 - Questions about the training dataset

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

#62 - 关于论文中一些细节的疑问

Issue - State: closed - Opened by lebron-2016 about 1 year ago - 1 comment

#61 - how to change the backbone?

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

#60 - Hugging face demo not working

Issue - State: closed - Opened by richardliu1111 about 1 year ago - 1 comment

#59 - "KeyError: 'dataset'" when load the page

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

GitHub / UX-Decoder/Segment-Everything-Everywhere-All-At-Once issues and pull requests