Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Edwina____ 2aac20f78d | 1 year ago | |
---|---|---|
src | 1 year ago | |
train_utils | 1 year ago | |
README.md | 1 year ago | |
deeplabv3_resnet50.png | 1 year ago | |
get_palette.py | 1 year ago | |
my_dataset.py | 1 year ago | |
predict.py | 1 year ago | |
requirements.txt | 1 year ago | |
results20211027-104607.txt | 1 year ago | |
train_multi_GPU.py | 1 year ago | |
validation.py | 1 year ago |
requirements.txt
├── src: 模型的backbone以及DeepLabv3的搭建
├── train_utils: 训练、验证以及多GPU训练相关模块
├── my_dataset.py: 自定义dataset用于读取VOC数据集
├── train.py: 以deeplabv3_resnet50为例进行训练
├── train_multi_GPU.py: 针对使用多GPU的用户使用
├── predict.py: 简易的预测脚本,使用训练好的权重进行预测测试
├── validation.py: 利用训练好的权重验证/测试数据的mIoU等指标,并生成record_mAP.txt文件
└── pascal_voc_classes.json: pascal_voc标签文件
deeplabv3_resnet50_coco.pth
文件,deeplabv3_resnet50_coco-cd0a2569.pth
torchrun --nproc_per_node=8 train_multi_GPU.py
指令,nproc_per_node
参数为使用GPU数量CUDA_VISIBLE_DEVICES=0,3
(例如我只要使用设备中的第1块和第4块GPU设备)CUDA_VISIBLE_DEVICES=0,3 torchrun --nproc_per_node=2 train_multi_GPU.py
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》