Comments (15)
Hi @kasteric
They are the same.
There are some misaligned file names between Installation guidelines and train.sh, and I will fix them.
Thanks for your comments!
from psalm.
Hi @pzhren
Thanks for your interest in our work. The prepare_coco_semantic_annos_from_panoptic_annos.py file is from mask2former, here. And I'll add it asap.
BTW, we also plan to release the converted files and may help you evaluate PSALM : )
from psalm.
from psalm.
Hi, may I ask if the LLM in the current PSALM has the ability for QA dialogue?
from psalm.
Line 6 in 4a078fa
Hi, is the JSON file corresponding to this line missing?
from psalm.
Hi @pzhren
This is a bug, instance_json_path
is deprecated in training and you can directly delete it. I have changed train.sh
And PSALM can do QA dialogue and you can find the corresponding results in paper appendix
from psalm.
I still could not find visual_prompt_segmentation_train.json, but i got coco_interactive_train_psalm.json and coco_interactive_val_psalm.json instead :)
from psalm.
Thank you for your prompt reply. It would be great if you could provide some small phrase segmentation demos. ---- Replied Message ---- FromEnming @.>Date4/15/2024 @.>CcAndy @.>, @.>SubjectRe: [zamling/PSALM] File missing (Issue #4) Hi @pzhren Thanks for your interest in our work. The prepare_coco_semantic_annos_from_panoptic_annos.py file is from mask2former, here. And I'll add it asap. BTW, we also plan to release the converted files and may help you evaluate PSALM : ) — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>
Hi, may I ask after I ran the "prepare_coco_semantic_annos_from_panoptic_annos.py", where the "datasets/coco/annotations/panoptic_val2017.json" is? Thanks!
from psalm.
Hi @z-stefanie
The panoptic and semantic datasets preparing is following mask2former , the dataset structure is the same as mask2former (or detectron2). And you need to download related files, like panoptic_val2017.json
, from COCO website.
from psalm.
Moreover, I will provide converted training and evaluating json file in this week. Please give me some time!
from psalm.
你好@z-stefanie 全景和语义数据集的准备遵循mask2former,数据集结构与 mask2former (或 detectorron2)相同。您需要
panoptic_val2017.json
从COCO 网站下载相关文件,例如。
okok,我懂了,感谢您!非常棒的工作!
from psalm.
Moreover, I will provide converted training and evaluating json file in this week. Please give me some time!
另外,我还想请教您一件事,就是现在支持在huggingface上将PSALM部署到本地吗?
部署好之后可以传入自己的图片路径和Prompt,得到它的回答不?(有无调用的范例或格式呢?)再次感谢您的非常棒的工作!
from psalm.
Hi all,
I've uploaded converted files and you can find instructions and downloading link here.
from psalm.
Hi @z-stefanie
#2 also ask the same question.
We do have a plan to provide a inference demo and this work is ongoing, will ping you when it's available.
from psalm.
@zamling 请问一下,本地部署的代码什么时候能够出来
from psalm.
Related Issues (16)
- Load Model error? HOT 4
- About inference code
- Question about multi-source data joint trainig HOT 2
- Error when Evaluation in Command Line HOT 4
- ValueError: matrix contains invalid numeric entries HOT 2
- How to fine-tune on my own dataset HOT 3
- Fail to finetune on my own dataset for anomaly detection task
- Visualization scripts for evaluation HOT 1
- dataset_coco_class_name under multi dataset training HOT 4
- Training with multiple nodes HOT 1
- Number of Epochs during Training HOT 1
- First stage scripts HOT 2
- Some questions about paper and code HOT 1
- Is mask decoder trained in the second stage? HOT 2
- Question about data overlap HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from psalm.