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
- pytorch==0.4.1
- python==3.5
- numpy
- torchvision
- matplotlib
- opencv-python
- dominate
- random
- collections
- shutil
Plesae download VOC12_aug dataset and unzip the dataset into data
folder.
Please download MIT imagenet pretrained resnet50-imagenet.pth, and put it into checkpoints
folder.
Please modify your configuration in options/base options.py
.
bash train.sh
- Modify the network and improve the accuracy
- Add Synchronous BN
under construction...
If you have any question, feel free to contact me or submit issue.