DeepLabV3+ is a state-of-the-art semantic segmentation network. It combines the strengths of DeepLabV3 and a powerful encoder-decoder architecture. The network employs atrous convolution to capture multi-scale contextual information effectively. It introduces a novel feature called the "ASPP" module, which utilizes parallel atrous convolutions to capture fine-grained details and global context simultaneously.
pip3 install wandb
pip3 install urllib3==1.26.6
Sign up and login in Cityscapes official website, then choose 'Download' to download the cityscapes dataset. Specify /path/to/cityscapes
to your Cityscapes path in later training process.
The Cityscapes dataset path structure should look like:
Cityscapes
├── leftImg8bit
│ ├── train
│ │ └── aachen
│ │ ├── aachen_000000_000019_leftImg8bit.png
│ │ └── ...
│ └── val
│
├── gtFine
│ ├── train
│ │ └── aachen
│ │ ├── aachen_000000_000019_gtFine_labelTrainIds.png
│ │ └── ...
│ └── val
│
├── license.txt
├── README
├── test.txt
├── train.txt
└── val.txt
Open config folder and set /path/to/cityscapes
in ./config/cityscapes_resnet50.py.
single gpu:
export CUDA_VISIBLE_DEVICES=0
nohup python3 trainer.py cityscapes_resnet50 1> train_deeplabv3.log 2> train_deeplabv3_error.log & tail -f train_deeplabv3.log
GPUs | FPS | ACC |
---|---|---|
BI-V100 | 6.14 | 77.35% |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。