날짜:
Game
- 공유 링크 만들기
- X
- 이메일
- 기타 앱
How often to display the alignment. (type:int default:0)
Controls network behavior. (type:int default:192)
How many imperfect samples between perfect ones. (type:int default:0)
Max memory to use for images. (type:int default:6000)
Index in continue_from Network at which to attach the new network defined by net_spec (type:int default:-1)
If set, exit after this many iterations. A negative value is interpreted as epochs, 0 means infinite iterations. (type:int default:0)
Final error rate in percent. (type:double default:0.01)
Range of initial random weights. (type:double default:0.1)
Weight factor for new deltas. (type:double default:0.001)
Decay factor for repeating deltas. (type:double default:0.5)
Decay factor for repeating deltas. (type:double default:0.999)
Just convert the training model to a runtime model. (type:bool default:false)
Convert the recognition model to an integer model. (type:bool default:false)
Use the training files sequentially instead of round-robin. (type:bool default:false)
Get info on distribution of weight values (type:bool default:false)
Train OSD and randomly turn training samples upside-down (type:bool default:false)
Network specification (type:string default:)
Existing model to extend (type:string default:)
Basename for output models (type:string default:lstmtrain)
File listing training files in lstmf training format. (type:string default:)
File listing eval files in lstmf training format. (type:string default:)
Starter traineddata with combined Dawgs/Unicharset/Recoder for language model (type:string default:)
When changing the character set, this specifies the traineddata with the old character set that is to be replaced (type:string default:)
댓글
댓글 쓰기