1.microsoft / OmniParserA simple screen parsing tool towards pure vision based GUI agentJupyter NotebookCC-BY-4.026K total2.2K forks+487 starsfrom 25,118 · score 6.19
2.IDEA-Research / Grounded-Segment-AnythingGrounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anythingopen-vocabulary-detectionopen-vocabulary-segmentationdata-generationautomatic-labeling-systemcaptionspeech+2 moreJupyter NotebookAPACHE-2.018K total1.6K forks+151 starsfrom 17,639 · score 5.02
3.WongKinYiu / yolov7Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorsscaled-yolov4yoloryolov3yolov4yolov7darknet+1 moreJupyter NotebookGPL-3.014K total4.3K forks+55 starsfrom 14,102 · score 4.03