- Welcome to my personal repository for exploring Detectron2! Here, I will be studying the algorithms in Detectron2, reading related papers, and summarizing my findings. My approach is to learn by applying, so I will be taking notes and assigning challenges to upgrade my current level.
The main technologies I will be using are PyTorch and PyLabel.
Some of the features of this repository include:
- Personal notes and challenges to upgrade skills
- Essential Detectron2 capabilities and power learning
- Notebooks from Colab and Kaggle, among other sources
To use this repository, you need to have Python 3.7 or higher and PyTorch 1.3 or higher installed.
- read them and try to upgrade them and make your own versions
- R-CNN
- RetinaNet
- Faster-RCNN
- RPN
- TensorMask
- PointRend
- DensePose
- ResNet and ResNeXt
- Introduction
- Technologies
- Features
- Setup
- Table of Contents
- Illustrations
- Scope of Functionalities
- Example of Use
- Project Status
- Sources
- Other Information
I will include illustrations of the algorithms, models, and datasets I'm working with.
My goal is to learn and master the functionalities of Detectron2, including object detection, instance segmentation, and keypoint detection.
I will provide code examples and demonstrations of how to use Detectron2 to solve real-world problems.
This is an ongoing project, and I will be updating the repository as I learn and progress.
I will be reading and summarizing papers related to Detectron2, as well as consulting the official documentation and community forums.
Feel free to contact me if you have any questions or suggestions for how to improve this repository.
augmentations # repo related to augmentations techniques, libraries and papers