1 Star 0 Fork 49

思想的光芒 / DeepSparkHub

forked from DeepSpark / DeepSparkHub 
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
README.md 3.07 KB
一键复制 编辑 原始数据 按行查看 历史

MobileSeg

Model description

MobileSeg models adopt encoder-decoder architecture and use lightweight models as encoder. These semantic segmentation models are designed for mobile and edge devices.

Step 1: Installation

git clone -b release/2.7 https://github.com/PaddlePaddle/PaddleSeg.git
cd PaddleSeg
pip3 install -r requirements.txt
pip3 install protobuf==3.20.3 
pip3 install urllib3==1.26.6
yum install mesa-libGL

Step 2: Preparing datasets

Go to visit Cityscapes official website, then choose 'Download' to download the Cityscapes dataset.

Specify /path/to/cityscapes to your Cityscapes path in later training process, the unzipped dataset path structure sholud look like:

cityscapes/
├── gtFine
│   ├── test
│   ├── train
│   │   ├── aachen
│   │   └── bochum
│   └── val
│       ├── frankfurt
│       ├── lindau
│       └── munster
└── leftImg8bit
    ├── train
    │   ├── aachen
    │   └── bochum
    └── val
        ├── frankfurt
        ├── lindau
        └── munster
# Datasets preprocessing
pip3 install cityscapesscripts

python3 tools/data/convert_cityscapes.py --cityscapes_path /path/to/cityscapes --num_workers 8

python3 tools/data/create_dataset_list.py /path/to/cityscapes --type cityscapes --separator ","

# CityScapes PATH as follow:
ls -al /path/to/cityscapes
total 11567948
drwxr-xr-x 4 root root         227 Jul 18 03:32 .
drwxr-xr-x 6 root root         179 Jul 18 06:48 ..
-rw-r--r-- 1 root root         298 Feb 20  2016 README
drwxr-xr-x 5 root root          58 Jul 18 03:30 gtFine
-rw-r--r-- 1 root root   252567705 Jul 18 03:22 gtFine_trainvaltest.zip
drwxr-xr-x 5 root root          58 Jul 18 03:30 leftImg8bit
-rw-r--r-- 1 root root 11592327197 Jul 18 03:27 leftImg8bit_trainvaltest.zip
-rw-r--r-- 1 root root        1646 Feb 17  2016 license.txt
-rw-r--r-- 1 root root      193690 Jul 18 03:32 test.txt
-rw-r--r-- 1 root root      398780 Jul 18 03:32 train.txt
-rw-r--r-- 1 root root       65900 Jul 18 03:32 val.txt

Step 3: Training

# Change '/path/to/cityscapes' as your local Cityscapes dataset path
data_dir=/path/to/cityscapes
sed -i "s#: data/cityscapes#: ${data_dir}#g" configs/_base_/cityscapes.yml
export FLAGS_cudnn_exhaustive_search=True
export FLAGS_cudnn_batchnorm_spatial_persistent=True

# One GPU
CUDA_VISIBLE_DEVICES=0 python3 train.py --config configs/mobileseg/mobileseg_mobilenetv3_cityscapes_1024x512_80k.yml --do_eval --use_vdl

# Eight GPUs
python3 -u -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 train.py \
       --config configs/mobileseg/mobileseg_mobilenetv3_cityscapes_1024x512_80k.yml \
       --do_eval \
       --use_vdl

Results

Cityscapes

Accuracy

Method Crop Size Lr schd FPS (BI x 8) mIOU
MobileSeg 512x1024 80000 28.68 0.726

Reference

马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
Python
1
https://gitee.com/Hcl11/deepsparkhub.git
git@gitee.com:Hcl11/deepsparkhub.git
Hcl11
deepsparkhub
DeepSparkHub
master

搜索帮助

344bd9b3 5694891 D2dac590 5694891