DeepLabv3.pytorch

This is a PyTorch implementation of DeepLabv3 that aims to reuse the resnet implementation in torchvision as much as possible. This means we use the PyTorch model checkpoint when finetuning from ImageNet, instead of the one provided in TensorFlow.

We try to match every detail in DeepLabv3, except that Multi-Grid other than (1, 1, 1) is not yet supported. On PASCAL VOC 2012 validation set, using the same hyperparameters, we reproduce the performance reported in the paper (GPU with 16GB memory is required). We also support the combination of Group Normalization + Weight Standardization:

Implementation	Normalization	Multi-Grid	ASPP	Image Pooling	mIOU
Paper	BN	(1, 2, 4)	(6, 12, 18)	Yes	77.21
Ours	BN	(1, 1, 1)	(6, 12, 18)	Yes	76.49
Ours	GN+WS	(1, 1, 1)	(6, 12, 18)	Yes	77.20

To run the BN experiment, after preparing the dataset as follows, simply run:

python main.py --train --exp bn_lr7e-3 --epochs 50 --base_lr 0.007

To test the trained model, use the same command except delete --train. To use our trained model (76.49):

wget https://cs.jhu.edu/~cxliu/data/deeplab_resnet101_pascal_v3_bn_lr7e-3_epoch50.pth -P data/

To run the GN+WS experiment, begin by downloading the GN+WS ResNet101 trained on ImageNet:

wget https://cs.jhu.edu/~syqiao/WeightStandardization/R-101-GN-WS.pth.tar -P data/
python main.py --train --exp gn_ws_lr7e-3 --epochs 50 --base_lr 0.007 --groups 32 --weight_std

Again, to test the trained model, use the same command except delete --train. To use our trained model (77.20):

wget https://cs.jhu.edu/~cxliu/data/deeplab_resnet101_pascal_v3_gn_ws_lr7e-3_epoch50.pth -P data/

Prepare PASCAL VOC 2012 Dataset

mkdir data
cd data
wget https://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
tar -xf VOCtrainval_11-May-2012.tar
cd VOCdevkit/VOC2012/
wget https://cs.jhu.edu/~cxliu/data/SegmentationClassAug.zip
wget https://cs.jhu.edu/~cxliu/data/SegmentationClassAug_Visualization.zip
wget https://cs.jhu.edu/~cxliu/data/list.zip
unzip SegmentationClassAug.zip
unzip SegmentationClassAug_Visualization.zip
unzip list.zip

Prepare Cityscapes Dataset

unzip leftImg8bit_trainvaltest.zip
unzip gtFine_trainvaltest.zip
git clone https://github.com/mcordts/cityscapesScripts.git
mv cityscapesScripts/cityscapesscripts ./
rm -rf cityscapesScripts
python cityscapesscripts/preparation/createTrainIdLabelImgs.py

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
data		data
LICENSE		LICENSE
README.md		README.md
cityscapes.py		cityscapes.py
deeplab.py		deeplab.py
main.py		main.py
pascal.py		pascal.py
utils.py		utils.py

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Repository files navigation

DeepLabv3.pytorch

Prepare PASCAL VOC 2012 Dataset

Prepare Cityscapes Dataset

About

Uh oh!

Releases

Packages

Languages

License

chenxi116/DeepLabv3.pytorch

Folders and files

Latest commit

History

Repository files navigation

DeepLabv3.pytorch

Prepare PASCAL VOC 2012 Dataset

Prepare Cityscapes Dataset

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Languages

Packages