jideilori / aerial_semantic_segmentation

Repository from Github https://github.comjideilori/aerial_semantic_segmentationRepository from Github https://github.comjideilori/aerial_semantic_segmentation

aerial_semantic_segmentation

Given 400 images. The data was split into train(60%),test(20%) and validation(20%).

The training set was then augmented using opencv to generate new images and it's correspoinding masks, bringing the total number of images to 3120.

This dataset was trained using Mobilenetv3small-Unet.

About

License:GNU General Public License v3.0


Languages

Language:Jupyter Notebook 100.0%