DeepLab in Detectron2

In this repository, we implement DeepLabV3 and DeepLabV3+ in Detectron2.

Installation

Install Detectron2 following the instructions.

Training

To train a model with 8 GPUs run:

cd /path/to/detectron2/projects/DeepLab
python train_net.py --config-file configs/Cityscapes-SemanticSegmentation/deeplab_v3_plus_R_103_os16_mg124_poly_90k_bs16.yaml --num-gpus 8

Evaluation

Model evaluation can be done similarly:

cd /path/to/detectron2/projects/DeepLab
python train_net.py --config-file configs/Cityscapes-SemanticSegmentation/deeplab_v3_plus_R_103_os16_mg124_poly_90k_bs16.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint

Cityscapes Semantic Segmentation

Cityscapes models are trained with ImageNet pretraining.

Method	Backbone	Output resolution	mIoU	model id	download
DeepLabV3	R101-DC5	1024×2048	76.7	-	- \| -
DeepLabV3	R103-DC5	1024×2048	78.5	28041665	model \| metrics
DeepLabV3+	R101-DC5	1024×2048	78.1	-	- \| -
DeepLabV3+	R103-DC5	1024×2048	80.0	28054032	model \| metrics

Note:

R103: a ResNet-101 with its first 7x7 convolution replaced by 3 3x3 convolutions. This modification has been used in most semantic segmentation papers. We pre-train this backbone on ImageNet using the default recipe of pytorch examples.
DC5 means using dilated convolution in res5.

Citing DeepLab

If you use DeepLab, please use the following BibTeX entry.

DeepLabv3+:

@inproceedings{deeplabv3plus2018,
  title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
  author={Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam},
  booktitle={ECCV},
  year={2018}
}

DeepLabv3:

@article{deeplabv32018,
  title={Rethinking atrous convolution for semantic image segmentation},
  author={Chen, Liang-Chieh and Papandreou, George and Schroff, Florian and Adam, Hartwig},
  journal={arXiv:1706.05587},
  year={2017}
}