模型训练不了 about rasa_nlu_chi HOT 4 OPEN

是你的训练数据太少了吗？

from rasa_nlu_chi.

同训练不了
Part I: train segmenter
words in dictionary: 200000
num features: 271
now do training
C: 20
epsilon: 0.01
num threads: 1
cache size: 5
max iterations: 2000
loss per missed segment: 3
C: 20 loss: 3 0.909091
C: 35 loss: 3 0.909091
C: 20 loss: 4.5 0.939394
C: 5 loss: 3 0.878788
C: 20 loss: 1.5 0.787879
C: 27.5 loss: 4.25 0.909091
C: 12.9813 loss: 4.76434 0.939394
C: 18.5 loss: 4.35 0.909091
C: 20.4813 loss: 4.8719 0.939394
C: 19.5307 loss: 4.35753 0.909091
C: 19.8419 loss: 4.68683 0.939394
C: 19.6481 loss: 4.5936 0.939394
best C: 20
best loss: 4.5
num feats in chunker model: 4095
train: precision, recall, f1-score: 1 1 1
Part I: elapsed time: 5 seconds.

Part II: train segment classifier
now do training
num training samples: 34
Killed
另外直接用examples中的demo-rasa_zh_movie.json也是显示Killed

from rasa_nlu_chi.

@shenyang077 应该是内存不够的锅，我把机器换成16G内存之后不会被自动killed了

from rasa_nlu_chi.

我问一下我代码跑了起来 但是我要训练自己的模型 怎么搞啊

from rasa_nlu_chi.