MichelleYang2017

Doesn't work?

2

``` class Back_Recompute(Layer): def __init__(self, nb_filter, bottleneck=False, dropout_rate=None, weight_decay=1e-4, **kwargs): self.nb_filter = nb_filter self.weight_decay = weight_decay self.bottleneck = bottleneck self.dropout_rate = dropout_rate super(Back_Recompute, self).__init__(**kwargs) def call(self, ip): global brcount concat_axis...

Hello,there is a problem about feature extraction in analysis.c file. In feature extraction process, there are many constant values(ie.spec_variability - 0.78f; info->tonality - 0.154723f;).Why are these constants and why use...

dataset written by myself

1

I want to know why the varaibels in __getitem__ function can be clear 0 in one epoch?

Hello.I want to know there is trained weights about gaussin distribution which std is 0.1.I try your weights it is vague.

Hello,I want to know, I have files in a submitted form,but I don't know how to use the code in public. It doesn't work

评测函数有问题

4

keras里面的评测的ACC本质上计算是这样的：label：[[0,1,0,0],[0,0,0,1]]，pred:[[0,0,0,0],[0,0,0,1]]准确率不是50%,而是87.5%

I just got into this field. I want to ask some questions, 1. Can the training data set only use one speaker's data? 2. Each audio on the official website...