Welcome on the object detection and segmentation in deep learning course page!
This page contains ressources for the object detection and segmentation class.
Slides
Slides are available here.
Pratical session
We use a Google Colab notebook for the pratical session. The notebook covers the concepts introduced during the course (see slides). In this notebook, we will train segmentation and object detection models on the balloon segmentation dataset, which only has one class: balloon. We’ll train these models from existing models pre-trained on the COCO dataset, available in Torchvision.
IMPORTANT: PLEASE COPY THE NOTEBOOK IN YOUR OWN DRIVE BEFORE START.
The notebook is available here.
Notes:
More content to customise object detection or segmentation models with torchvision will be available soon.
Acknowledgement
This course is based on the Standord’s object detection and image segmentation course and Charles Deledalle’s course on machine learning for image processing. Thanks to authors for their work!