File missing

[pzhren]

File missing

[zamling]

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!

[zamling]

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 : )

[pzhren]

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: ***@***.***>

[pzhren]

Hi, may I ask if the LLM in the current PSALM has the ability for QA dialogue?

[pzhren]

PSALM/scripts/train.sh

Line 6 in 4a078fa

--instance_json_path "/path/to/instruction_segmentation_train.json" \

Hi, is the JSON file corresponding to this line missing?

[zamling]

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

[kasteric]

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 :)

[z-stefanie]

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！

[zamling]

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.

[zamling]

Moreover, I will provide converted training and evaluating json file in this week. Please give me some time!

[z-stefanie]

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！

[z-stefanie]

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！

[zamling]

Hi all,
I've uploaded converted files and you can find instructions and downloading link here.

[zamling]

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.

[tianbuwei]

@zamling 请问一下，本地部署的代码什么时候能够出来