运行ExtractMel.py出错

xuanjihe / speech-emotion-recognition

speech emotion recognition using a convolutional recurrent networks based on IEMOCAP

389 stars 142 forks source link

运行ExtractMel.py出错 #16

Closed jasonlinuxzhang closed 5 years ago

jasonlinuxzhang commented 5 years ago

Traceback (most recent call last): File "ExtractMel.py", line 389, in read_IEMOCAP() File "ExtractMel.py", line 200, in read_IEMOCAP train_data[train_num,:,:,0] = (part -mean1)/(std1+eps) ValueError: operands could not be broadcast together with shapes (300,40) (20,)

请问这是什么原因呢？

xuanjihe commented 5 years ago

已经解决，zscore.py里面的filter_num=20,ExtractMel.py里面的filter_num=40