xiaoyaoxiaoxian
Results
2
issues of
xiaoyaoxiaoxian
Hi, I have a question with my_crossentropy loss. The loss is as follows. When I refer to the usage of K.binary_crossentropy, I find that the y_true should be the first...
features[NB_BANDS+2*NB_DELTA_CEPS] -= 1.3; features[NB_BANDS+2*NB_DELTA_CEPS+1] -= 0.9; features[NB_BANDS+3*NB_DELTA_CEPS] = .01*(pitch_index-300); features[0] -= 12; features[1] -= 4; I donnot know why 1.3 0.9 12 and 4 is subtracted in feature excact funciton....