<

Detectron2

Welcome, it's great to have you here. Want to hear more about How you can separate image objects using Detectron2 Python mudule

Image segmentation.

Detectron2 is Facebook AI Research's next generation library that provides state-of-the-art detection and segmentation algorithms. It supports a number of computer vision research projects and production applications in Facebook. Please find the details on its official link at https://github.com/facebookresearch/detectron2

I used LVIS dataset at https://www.lvisdataset.org/ that has already trained models for shirt and clothes images. Other datasets are also available at COCO. I used a pre-trained model named "X101-FPN". This model can segment different objects including fashion features such as shirt, jean, etc.

See Getting Started with Detectron2, and the Colab Notebook at https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5 to learn about basic usage.