양산형? 하이퍼네트워크

다운로드 https://mega.nz/file/Ub1jHbIC#znwPnUxcyYZjVNZT99Qny_SUcWQHxNuauaN-PTlFm5I


적용


미적용


학습 정보

[1.0, 0.5, 1.0]

Activation function is swish

Weight initialization is Normal

Layer norm is set to False

Dropout usage is set to False

LR 0.0001:1000, 0.00005:2000, 0.000025:3000, 0.00001:5000, 0.000005:10000

MAX steps 10000 

Batch size 1