detectron2/projects/DeepLab/README.md

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}
}