浏览代码

Update docs

/MLA-1734-demo-provider
Ervin Teng 5 年前
当前提交
00c5efc4
共有 1 个文件被更改,包括 1 次插入1 次删除
  1. 2
      docs/Training-Configuration-File.md

2
docs/Training-Configuration-File.md


too large `memory_size` will slow down training.
- Adding a recurrent layer increases the complexity of the neural network, it is
recommended to decrease `num_layers` when using recurrent.
- It is required that `memory_size` be divisible by 4.
- It is required that `memory_size` be divisible by 2.
## Self-Play

正在加载...
取消
保存