Architecture | 1x1 Convolution, ASPP, Batch Normalization, Dilated Convolution, ResNet |
---|---|
Backbone Layers | 101 |
SHOW MORE |
Architecture | 1x1 Convolution, ASPP, Batch Normalization, Dilated Convolution |
---|---|
ID | 28054032 |
SHOW MORE |
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.
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
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.
@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}
}
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 |