[GitHub] [incubator-mxnet] eureka7mt commented on issue #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss

2019-03-07 Thread GitBox
eureka7mt commented on issue #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss URL: https://github.com/apache/incubator-mxnet/pull/13612#issuecomment-470771170 Maybe the broadcast_mul isn't necessary.I think that a NDArray * a NDArray will do broadcast_mul automatically. --

[GitHub] [incubator-mxnet] eureka7mt commented on issue #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss

2019-03-06 Thread GitBox
eureka7mt commented on issue #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss URL: https://github.com/apache/incubator-mxnet/pull/13612#issuecomment-470414059 @wkcn It could be a scalar for classifying a single class.But for multi-class and multi-label classifying,it should be a te

[GitHub] [incubator-mxnet] eureka7mt commented on issue #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss

2019-03-06 Thread GitBox
eureka7mt commented on issue #13612: add pos_weight for SigmoidBinaryCrossEntropyLoss URL: https://github.com/apache/incubator-mxnet/pull/13612#issuecomment-470401972 Add the if-else statement make an error.Though the default value of pos_weight is set to be 1,the pos_weight is an (1,N) ND