OmniParser
OmniParser copied to clipboard
A simple screen parsing tool towards pure vision based GUI agent
 Cannot be used。
Am i missing something? Just a couple days ago I was able to install adn get coordiantes along with the parsed screen elements. Was that removed?
The original model seems to run very slowly.
Hello! I was wondering where to find the documentation of the `omniparser`. From the [demo](https://huggingface.co/spaces/microsoft/OmniParser), I can find two thresholds, but couldn't find what they are. Also, where can I...
When using the gradio demo to recognize Chinese characters, the output often appears as gibberish or incorrect characters that are non-sense. I would like to know how to address this...
**Description:** When running the command below to test icon classification with the BLIP-2 model, I encountered a tensor mismatch error. Despite following the instructions referenced in the error message, the...
I found that the digital labels on the picture and the index of the PARED_CONTENT_LIST can be corresponding. It's just that the two are different. For example, the text of...
Hello author, OmniParser is a good idea. I have a question to ask now. According to my understanding, YOLOv8 is trained using purely icon based control data, right? Control data...
error at line 61 of gradio_demo.py syntax error because of improper use of quotes within the f-string
Hii, I tried making some changes, - Used logging instead of print statements for better tracking and debugging. - Added try-except blocks to handle potential errors during processing and exporting....