ONNX and OpenVINO Compatible Yolact Model
-
The yolact model is a simple, fully convolutional model for real-time instance segmentation
-
YOLACT is an acronym for "You Only Look At CoefficienTs," which reflects the core philosophy behind this state-of-the-art real-time instance segmentation model
-
It leverages the openvino and onnx frameworks for inference.
-
Currently, only the image inference functionality is operational.
-
After the conversion process, refactoring the remaining parts becomes easier.
Installation and Issue Resolution
- To explore the original model or download the pretrained weights visit the Yolact GitHub Repo.
- For OpenVino installation issues and further details, please refer to the OpenVino GitHub Repo.
You Only Look At CoefficienTs
██╗ ██╗ ██████╗ ██╗ █████╗ ██████╗████████╗
╚██╗ ██╔╝██╔═══██╗██║ ██╔══██╗██╔════╝╚══██╔══╝
╚████╔╝ ██║ ██║██║ ███████║██║ ██║
╚██╔╝ ██║ ██║██║ ██╔══██║██║ ██║
██║ ╚██████╔╝███████╗██║ ██║╚██████╗ ██║
╚═╝ ╚═════╝ ╚══════╝╚═╝ ╚═╝ ╚═════╝ ╚═╝
Installation
- Clone this repository and enter it:
git clone https://github.com/Abdullah-Elkasaby/yolact-isntance-segmentation-openvino.git cd 238-yolact-image-segmentation
- Set up the environment using one of the following methods:
- Using Anaconda
- Run
conda env create -f environment.yml
- Run
- Manually with pip
- Set up a Python3 environment (e.g., using virtenv).
- Install Pytorch 1.0.1 (or higher) and TorchVision.
- Install some other packages:
# Cython needs to be installed before pycocotools pip install cython pip install opencv-python pillow pycocotools matplotlib
- Using Anaconda