Some GUI problems
Levine66 opened this issue · comments
Thanks for your tools. I am trying to use this tool in my equipment. And i meet some problems during run the segment_anything_annotator.py.
I have a server with GPU, which is a Linux system without GUI. It's totally terminal system. I use my Macbook to link the server with SSH tool. And I have created embedding and onnx model in server.
When I want to annotate my images, the PyQt doesn't work well and export error:Could not connect to any X display and QLibraryPrivate::unload succeeded on "/usr/lib/x86_64-linux-gnu/qt5/plugins/platforms/libqxcb.so". I have tried to fix it by reinstall pyqt and install PYQT Integration in my VSCode. But it is not useful for me.
I would like to ask two questions:
- How can i solve my PyQt problems? Can you give me some advices?
- How to use your tool in Macbook and GPU server more more convenient?
I am looking forward to your answer
I would recommend following the steps listed in the README which describe this exact scenario.
You do not need a GPU to run the tool, only to get the image embeddings. So I would suggest copying your images to the server, extracting your embeddings on the server, and compiling the onnx models there (using the helpers I provided, copy them to your server).
Next, copy the images, embeddings and models locally. Install SALT locally. The onnx model is fast enough for interactive use on a CPU.
Thanks for your reply. I have tried this way after submitting this issues. This works on my laptop. I had considered that CPU is not fast enough before submitting this issues, and it is totally wrong. Thanks for your tools again, i would like to use it and make some contribution to this project if possible.
The SAM paper mentions that their decoder (the ONNX model) was shipped to their annotators, who I assume wouldn't have very fast GPUs locally. Also their online demo runs the decoder on your browser. I just wrote a tool to do the same thing that their demo does. :)