If you haven't seen YOLACT (think YOLO with masks) in action, check out the insane quality of this video of a giraffe. The output is similar to Mask R-CNN, but it's a single shot detector and can achieve real-time FPS! I made a Google Colab tutorial for anyone who wants to try it.
www.immersivelimit.com/tutorials/yolact-with-google-colab
'Deep Learning > image_segmentation' 카테고리의 다른 글
| semantic segmentation에서는 resize를 하지 않고 원본 이미지 그대로 사용하는건가요? (0) | 2020.04.28 |
|---|
