1 Star 8 Fork 3

monkey_cici / mmsegmentation

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
克隆/下载
npu.md 4.77 KB
一键复制 编辑 原始数据 按行查看 历史

NPU (HUAWEI Ascend)

Usage

Please refer to the building documentation of MMCV to install MMCV on NPU devices

Here we use 4 NPUs on your computer to train the model with the following command:

bash tools/dist_train.sh configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py 4

Also, you can use only one NPU to train the model with the following command:

python tools/train.py configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py

Models Results

Model mIoU Config Download
deeplabv3 78.85 config log
deeplabv3plus 79.23 config log
hrnet 78.1 config log
fcn 74.15 config log
icnet 69.25 config log
pspnet 77.21 config log
unet 68.86 config log
upernet 77.81 config log
apcnet 78.02 config log
bisenetv1 76.04 config log
bisenetv2 72.44 config log

Notes:

  • If not specially marked, the results on NPU with amp are the basically same as those on the GPU with FP32.

All above models are provided by Huawei Ascend group.

Python
1
https://gitee.com/monkeycc/mmsegmentation.git
git@gitee.com:monkeycc/mmsegmentation.git
monkeycc
mmsegmentation
mmsegmentation
main

搜索帮助