Train Instance Segmentation Model with Detectron2 | Tutorial | Custom Dataset | Google Colab
Detectron2 is a popular PyTorch based modular computer vision model library. It is the second iteration of Detectron, originally written in Caffe2. The Detectron2 system allows you to plug in custom state of the art computer vision technologies into your workflow.
Chapters:
0:00 Introduction
1:20 Setting up python environment
2:31 Inference using pre-trained model
3:56 Getting open source data from Roboflow Universe
8:20 Training segmentation model
11:08 Outro
Roboflow - https://roboflow.com
Roboflow Universe: https://universe.roboflow.com
"How to Train Detectron2 on Custom Object Detection Data" Blog Post: https://blog.roboflow.com/how-to-trai...
"How to Train YOLOv5-Classification on a Custom Dataset" Blog Post: https://blog.roboflow.com/train-yolov...
Official Roboflow Detectron2 Segmentation Colab Training Colab: https://colab.research.google.com/dri...
📓 Learn more about Detectron2 and other Computer Vision libraries with Roboflow Notebooks: https://github.com/roboflow-ai/notebooks
Stay up to date with the projects I'm working on at https://github.com/roboflow-ai and https://github.com/SkalskiP! ⭐