Skip to main content

dnn-tuning

【DNN调参】当用户说"DNN调参"、"深度学习调参"、"调整网络结构"、"调整dropout"、"DNN过拟合"时使用。基于 Optuna TPE 贝叶斯优化,搜索网络架构(层数、宽度、dropout)和训练参数(learning_rate、weight_decay、batch_size),诊断驱动约束搜索空间。前置条件:需先用 dnn-modeling 训练出基线模型。

Jump to install

Source facts

Repository
aliyun/qwen-dianjin
Last source activity
May 20, 2026 at 14:16
Detected SKILL.md language
Chinese
Stars
604
Forks
68

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.