jahongir7174 / DeepLab-pt

DeepLabV3 plus implementation using PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DeepLabV3+

DeepLabV3+ implementation for Semantic Segmentation using PyTorch

Train

  • Run python main.py for training

Dataset structure (similar to CamVid dataset)

├── Dataset folder 
    ├── train
        ├── 1111.png
        ├── 2222.png
    ├── train_labels
        ├── 1111_L.png
        ├── 2222_L.png
    ├── class_dict.csv

Note

  • default feature extractor is EfficientNetV2-S
  • changing configuration of training, change parameters in utils/config.py
  • default loss function is weighted cross entropy

About

DeepLabV3 plus implementation using PyTorch

License:Apache License 2.0


Languages

Language:Python 100.0%