当前位置:网站首页>【PaddleClas】常用命令
【PaddleClas】常用命令
2022-07-05 17:50:00 【mtl1994】
【PaddleClas】常用命令
1.生成数据集
需要修改 build_product.yaml
python python/build_gallery.py -c configs/build_product.yaml -o IndexProcess.data_file="D:\Paddle\PaddleClas\out\recognition_demo_data_v1.0\gallery_sg\data_file.txt" -o IndexProcess.index_path="D:\Paddle\PaddleClas\out\recognition_demo_data_v1.0\gallery_sg\index"
3.预测
python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_voc.yml --infer_dir=/home/aiuser/mtl/data/sg/test --output_dir=./sg_out_put/ --draw_threshold=0.5 -o weights=./output/ppyolo_r50vd_dcn_voc/model_final
4.导出
python tools/export_model.py -c configs/ppyolo/ppyolo_r50vd_dcn_voc.yml \
--output_dir=./inference_model \
-o weights=output/ppyolo_r50vd_dcn_voc/model_final
可选参数列表
以下列表可以通过--help查看
| FLAG | 支持脚本 | 用途 | 默认值 | 备注 |
|---|---|---|---|---|
| -c | ALL | 指定配置文件 | None | 配置模块说明请参考配置模块 |
| -o | ALL | 设置配置文件里的参数内容 | None | 使用-o配置相较于-c选择的配置文件具有更高的优先级。例如:-o use_gpu=False max_iter=10000 |
| -r/–resume_checkpoint | train | 从某一检查点恢复训练 | None | -r output/faster_rcnn_r50_1x/10000 |
| –eval | train | 是否边训练边测试 | False | |
| –output_eval | train/eval | 编辑评测保存json路径 | 当前路径 | --output_eval ./json_result |
| –fp16 | train | 是否使用混合精度训练模式 | False | 需使用GPU训练 |
| –loss_scale | train | 设置混合精度训练模式中损失值的缩放比例 | 8.0 | 需先开启--fp16后使用 |
| –json_eval | eval | 是否通过已存在的bbox.json或者mask.json进行评估 | False | json文件路径在--output_eval中设置 |
| –output_dir | infer | 输出预测后可视化文件 | ./output | --output_dir output |
| –draw_threshold | infer | 可视化时分数阈值 | 0.5 | --draw_threshold 0.7 |
| –infer_dir | infer | 用于预测的图片文件夹路径 | None | |
| –infer_img | infer | 用于预测的图片路径 | None | 相较于--infer_dir具有更高优先级 |
| –use_vdl | train/infer | 是否使用VisualDL记录数据,进而在VisualDL面板中显示 | False | VisualDL需Python>=3.5 |
| –vdl_log_dir | train/infer | 指定 VisualDL 记录数据的存储路径 | train:vdl_log_dir/scalar infer: vdl_log_dir/image | VisualDL需Python>=3.5 |
边栏推荐
- Matlab reference
- ISPRS2020/云检测:Transferring deep learning models for cloud detection between Landsat-8 and Proba-V
- Sophon Base 3.1 推出MLOps功能,为企业AI能力运营插上翅膀
- EPM related
- 通过SOCKS代理渗透整个内网
- 修复漏洞 - mysql 、es
- Sophon CE社区版上线,免费Get轻量易用、高效智能的数据分析工具
- Why is February 28 in the Gregorian calendar
- ITK Example
- [performance test] full link voltage test
猜你喜欢

How awesome is the architecture of "12306"?

PMP认证需具备哪些条件啊?费用多少啊?

flask接口响应中的中文乱码(unicode)处理

Mask wearing detection based on yolov3

"Xiaodeng in operation and maintenance" is a single sign on solution for cloud applications

To solve the problem of "double click PDF file, pop up", please install Evernote program

Sophon Base 3.1 推出MLOps功能,为企业AI能力运营插上翅膀

ISPRS2022/雲檢測:Cloud detection with boundary nets基於邊界網的雲檢測

Daily exercise: a series of dates

ISPRS2022/云检测:Cloud detection with boundary nets基于边界网的云检测
随机推荐
提高應用程序性能的7個DevOps實踐
EPM相关
Please tell me why some tables can find data by writing SQL, but they can't be found in the data map, and the table structure can't be found
Which platform of outer disk gold is regular and safe, and how to distinguish it?
Ten capabilities that cyber threat analysts should have
Leetcode exercise - 206 Reverse linked list
EasyCVR平台通过接口编辑通道出现报错“ID不能为空”,是什么原因?
Daily exercise: a series of dates
“12306” 的架构到底有多牛逼?
[TestLink] testlink1.9.18 solutions to common problems
Thesis reading_ Medical NLP model_ EMBERT
Sophon CE Community Edition is online, and free get is a lightweight, easy-to-use, efficient and intelligent data analysis tool
Binder开辟线程数过多导致主线程ANR异常
Disorganized series
Cmake tutorial Step3 (requirements for adding libraries)
Six bad safety habits in the development of enterprise digitalization, each of which is very dangerous!
使用QT遍历Json文档及搜索子对象
"Xiaodeng in operation and maintenance" is a single sign on solution for cloud applications
ISPRS2022/云检测:Cloud detection with boundary nets基于边界网的云检测
Sophon Base 3.1 推出MLOps功能,为企业AI能力运营插上翅膀