Skip to content

Latest commit

 

History

History
41 lines (22 loc) · 526 Bytes

README.md

File metadata and controls

41 lines (22 loc) · 526 Bytes

Semantic Segmentation - Drone Deploy Aerial Dataset

Semantic segmentation implementation based on pytorch-lightning.

Training

using main.py with predefined data paths (TODO: add hparams)

python main.py

Prediction

Prediction example at

Inference.ipynb 

file

Results

Example results on Unet, after 16 epochs, trained on 768x768 resolution.

results

Todo's

  • ENet
  • pspnet
  • add hparams