OmniParser
OmniParser copied to clipboard
microsoft
A simple screen parsing tool towards pure vision based GUI agent
I want to use the page data of our own APP for further fine-tuning training based on OmniParser to improve the accuracy of recognition, but I don't know how to...
Good work. Can you provide the code of evaluating your model on screenspot and other dataset as mentioned in the paper？
2024-12-04 23:44:04 finish processing 2024-12-04 23:44:04 2024-12-04 23:44:04 image 1/1 /usr/src/app/imgs/saved_image_demo.png: 384x640 122 0s, 31.8ms 2024-12-04 23:44:04 Speed: 3.9ms preprocess, 31.8ms inference, 2.3ms postprocess per image at shape (1, 3,...
Hello, Thank you for making this wonderful tool. I was attempting to set it up on my machine and it seems that the setup instructions are incomplete in the readme...
Hi, thanks for the incredible research. I really wanted to learn more about the OCR module used in this paper. Can anyone help me to understand what type of OCR...
Is there any kind of free/paid api i could use to build with omniparser? Please help me out on this one.
The icon detection is supper great, however the icon classification ( parsed_content_list 'content' field is not so accurate ) If more accurate icon detection result we can feed to LLM...
Thank you for the excellent work ！！！ In the paper, I find some describtion " Specifically, we curate a dataset of interactable icon detection dataset, containing 67k unique screenshot images,...
Hello. I tried running `omniparser.py` and got this error: ``` ❯ python omniparser.py Traceback (most recent call last): File "/home/arthur/dev/ai/OmniParser/omniparser.py", line 1, in from utils import get_som_labeled_img, check_ocr_box, get_caption_model_processor, get_dino_model,...
