DeepLabV3+

Backbone Layers	101
Output Resolution	1024×2048

ID	28054032
Backbone Layers	101
Output Resolution	1024×2048

Parameters

Backbone Layers 101

Training Data Cityscapes

Training Resources 8 NVIDIA V100 GPUs

Training Time

Architecture	1x1 Convolution, ASPP, Batch Normalization, Dilated Convolution, ResNet
Backbone Layers	101
Output Resolution	1024×2048
SHOW MORE
SHOW LESS

Parameters 60 Million

Backbone Layers 101

File Size 227.35 MB

Training Data Cityscapes

Training Resources 8 NVIDIA V100 GPUs

Training Time

Architecture	1x1 Convolution, ASPP, Batch Normalization, Dilated Convolution
ID	28054032
Backbone Layers	101
Output Resolution	1024×2048
SHOW MORE
SHOW LESS

README.md

Summary

DeepLabv3+ is a semantic segmentation architecture that improves upon DeepLabv3 with several improvements, such as adding a simple yet effective decoder module to refine the segmentation results.

How do I evaluate this model?

Model evaluation can be done as follows:

cd /path/to/detectron2/projects/DeepLab
python train_net.py --config-file configs/Cityscapes-SemanticSegmentation/deeplab_v3_R_103_os16_mg124_poly_90k_bs16.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint

How do I train this model?

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_R_103_os16_mg124_poly_90k_bs16.yaml --num-gpus 8

You can follow the Getting Started guide on Colab to see how to train a model.

You can also read the official Detectron2 documentation.

Citation

@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}
}

Results

Semantic Segmentation on Cityscapes val

Semantic Segmentation

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Cityscapes val	DeepLabV3+ (R103-DC5)	mIoU	80.0	# 1
Cityscapes val	DeepLabV3+ (R101-DC5)	mIoU	78.1	# 4