rockeycoss / prompt-segment-anything Goto Github PK

This looks like a great tool, but unfortunately it's CLI, and in a end-program, we should be avoiding sub-process as much as possible. Is it possible to get either directions for programmable usage, or a method for importing and using functions via python?

Hello, as shown below, I have run "python setup.py build install" but still get this error.
Is there anything I have not build yet?
Thanks!

Thank you for your amazing work.
I already test the demo on huggingface.

However, I have some issues.
Following your instructions, I get an error with "from mmcv import Config" in the Evaluate Metrics step and Gradio Demo.

Below are the results of checking the version when the command line uploaded on GitHub is installed.
pip show mmdet | grep Version : Version: 3.0.0
pip show mmcv |grep Version : Version: 2.0.0

If i downgrade to mmcv-full 1.7.1 instead of mmcv(v2.0.0), it allows the Gradio Demo to work and generate a URL,
but the Evaluate Metrics still doesn't work.

嗨大佬，你是我找了好久第一个开源了evaluate的sam项目，非常牛逼！
想问一下你还考虑做别的下游任务嘛，因为我关注到你这只有实例分割的任务，要是有别的任务就好了

Reference: https://github.com/ChaoningZhang/MobileSAM

Our project performs on par with the original SAM and keeps exactly the same pipeline as the original SAM except for a change on the image encode, therefore, it is easy to Integrate into any project.

MobileSAM is around 60 times smaller and around 50 times faster than original SAM, and it is around 7 times smaller and around 5 times faster than the concurrent FastSAM. The comparison of the whole pipeline is summarzed as follows:

Best Wishes,

Qiao

how to train Prompt-Segment-Anything for instance segmentation with my own dataset

rockeycoss yyds!

Trying to access the FocalNet+DINO detector checkpoint gives this error:

2023-09-06 11:59:10 ERROR 409: Public access is not permitted on this storage account..

This is true of all the checkpoints listed in the source repo https://github.com/FocalNet/FocalNet-DINO

大佬你好，有没有详细文档介绍pipeline流程，test和推理的流程是怎样的，怎样流过文件的