OmniParser
OmniParser copied to clipboard
microsoft
A simple screen parsing tool towards pure vision based GUI agent
Hello, Running the gradio example results in a virus-like (at least per my antivirus) file to be required. Several [others are](https://www.google.com/search?q=frpc+_windows_amd64&rlz=1C1GCEU_enUS1030US1030&oq=frpc_wind&gs_lcrp=EgZjaHJvbWUqCAgBEAAYChgeMgYIABBFGDkyCAgBEAAYChgeMgYIAhAAGB4yBggDEAAYHjIGCAQQABgeMgYIBRAAGB4yBggGEAAYHjIGCAcQABgeMgYICBAAGB4yBggJEAAYHtIBCDcwNTJqMGo0qAIAsAIB&sourceid=chrome&ie=UTF-8) reporting [the issue](https://stackoverflow.com/questions/79322598/could-not-create-share-link-missing-file-gradio-frpc-windows-amd64-v0-3) as well. **Steps to reproduce**: 1....
https://huggingface.co/openbmb/MiniCPM-o-2_6  Have you thought about testing this model ? I am finding it interesting as Minicpm team is developing good models since last year plus they are using some...
Assuming the controlled VM is loaded with plenty local data, can I use OmniParser to drive VM-installed MATLAB/JupyterLab etc. to do automated data analysis? It seems transcripting icons and texts...
Hi, I have a mac, and i've installed everything according to your instructions. OmniParser works perfectly, however OmniTool is not - i get this screen:  And these are my...
Met this prob when running the script gradio_demo.py. Detailed traceback as follows: C:\Users\Jawk\.conda\envs\omni\python.exe C:\Users\Jawk\PycharmProjects\OmniParser\gradio_demo.py Traceback (most recent call last): File "C:\Users\Jawk\PycharmProjects\OmniParser\gradio_demo.py", line 11, in from util.utils import check_ocr_box, get_yolo_model, get_caption_model_processor,...
hello, thanks for your great job. In the screenspot pro eval code, I get the error： “ImportError: cannot import name 'get_pred_phi3v' from 'models.util.utils'” Where is this function implemented？
Hi, First of all, thanks for your great work on Omniparser V2! After reviewing the code in demo.ipynb, I understand that the workflow of Omniparser V2 involves: 1. Using an...
auto download these: ``` "icon_detect/train_args.yaml", "icon_detect/model.pt", "icon_detect/model.yaml", "icon_caption/config.json", "icon_caption/generation_config.json", "icon_caption/model.safetensors" ```
Hi there Any chance we'll see a quantized version (gguf, onnx, etc) for better CPU performance? I haven't tried yet using HF's `load_in_4bit` kind of options so I'm not sure...
