A realtime frame-by-frame segmentation on user-given video input.

Deeplabv3-MobileNetV3-Large is constructed by a Deeplabv3 model using the MobileNetV3 large backbone. The pre-trained model has been trained on a subset of COCO train2017, on the 20 categories that are present in the Pascal VOC dataset.

The accuracies of the pre-trained model evaluated on COCO val2017 dataset are listed below.

Model structure	              Mean IOU	Global Pixelwise Accuracy
deeplabv3_mobilenet_v3_large	  60.3	          91.2

-OpenCV

-PyTorch

-ONNX

-Tensorflow Lite

-Python

-Version Control: Git & GitHub

git clone https://github.com/vivupadi/Segmentation_app.git

cd Segmentation_app/src

python -m venv venv

source venv/bin/activate # On Windows: venv\Scripts\activate

pip install -r requirements.txt

python load_model.py

This project is licensed under the MIT License - see the LICENSE file for details.