zhly0
zhly0
@wjj19950828 你好，因为硬件只支持tflite格式，所以需要将paddle模型转换成tflite，另外，官网中要求tf的版本是1.14，如果使用不同的版本，会导致转换结果不一致吗
@kalyo-zjl did you use cosin distance instead of euclidean distance?
@xskxushaokai ，个人觉得，文章里面的意思是从center point里面回归所有的值，只不过所有的值，是指的相对于上一个层级的偏置。这样更合理一点，更好回归一点。
Hi，have you solve the problem？I have the same problem Thanks！
hi,@alebzk: from your issue,I learned a lot,I am new to pitch detection.If my training sample's sample rate is 16000,is the macro define PITCH_BUF_SIZE need to change?What is the relation between...
Hi，guys，learned many things from your discussion，wandering when I use a 16k hz training samples，do I need to change the code or not need to change the code?
@Jintao-Huang，能帮忙看下吗
sorry，it‘s a video modality_av.avi,I use one video as input,use it's audio to alignment with it's video,get modality_av.avi video file,the modality_av.avi video introduced some noise compared with it's original wav.
you can refer to https://github.com/zhly0/facenet-face-cluster-chinese-whispers-/issues/8