OmniParser
OmniParser copied to clipboard
microsoft
A simple screen parsing tool towards pure vision based GUI agent
It has come to our attention that the OmniParser project uses a dependency, `ultralytics`, which is licensed under the AGPL. This license requires that any software linking to it must...
After setting up the environment by following the tutorial, I ran `gradio_demo.py` and encountered the following error: ``` > python .\gradio_demo.py [2024-11-05 18:06:25,042] [ WARNING] easyocr.py:80 - Neither CUDA nor...
Can the granularity of image element recognition be adjusted? When I recognize images of tables, I find that each row in each cell is recognized as a separate element. Is...
hi all, is there a way to get ActionMatching? i see it in utils but i can't find any example to use it looks like the file is there but...
This commit removed `.pyc` files, which are typically excluded from the git repository and listed in `.gitignore`.
### Description This pull request eliminates redundant imports of `torch` and `PIL.Image` in the code. Currently, these libraries are imported multiple times in different places, leading to unnecessary duplication. This...
#### Description: In the current code, there are multiple imports of `torch` and `PIL.Image`. This redundancy can be eliminated by consolidating these imports into a single block to maintain cleaner...
Thank you for this impressive work -really interesting. I had a look at the paper, blog post and here, but I cannot see any indication of where the dataset is...
This is a great job, may I ask when the dataset & training code will be released?
OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory weights/omniparser/icon_caption_blip2. How to fix this??
