cescigl

keras更新后出现 Exception: Regularizers cannot be reused

5

具体的代码是这个 model2.add(TimeDistributed(Convolution2D(64, 3, 3, border_mode='valid', W_regularizer=l2(0.01), activity_regularizer=activity_l2(0.01)))) 如果去掉activity_regularizer就正常了，tf和th都试了，都会报这个异常

[Feature] The newly added Bocha search function does not turn on the switch that returns summary, and it is recommended to turn on by default.

2

### MaxKB Version 1.10.3 ### Please describe your needs or suggestions for improvements 他其实是一个接口参数，设置为Ture就行，或者在界面像填入apikey一样，新加一个参数也行。 ### Please describe the solution you suggest _No response_ ### Additional Information _No response_