Skip to content

Latest commit

 

History

History
40 lines (26 loc) · 799 Bytes

README.md

File metadata and controls

40 lines (26 loc) · 799 Bytes

DUpsampling

This repo is an unofficial pytorch implementation of CVPR19 paper: Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation: https://arxiv.org/abs/1903.02120

Installation

  • pytorch==0.4.1
  • python==3.5
  • numpy
  • torchvision
  • matplotlib
  • opencv-python
  • dominate
  • random
  • collections
  • shutil

Dataset and pretrained model

Plesae download VOC12_aug dataset and unzip the dataset into data, and modify your configuration in options/base options.py.

Usage

bash train.sh

Segmentation results on val set

To do

  • Add softmax with temperature
  • Modify the network and improve the accuracy

under construction...

If you have any question, feel free to contact me or submit issue.