Comments (16)
有人复现出训练过程么,方便请教么
from nkf-aec.
肯定不可以这样操作,如果loss是估计回声和真实回声的欧式距离,那么反向的时候梯度肯定要对数学建模部分的卡尔曼滤波进行反向,我的建议是计算数学方法的凯尔曼滤波器系数和网络输出的滤波器系数的距离。或者固定数学建模部分,使用最后的loss。
from nkf-aec.
肯定不可以这样操作,如果loss是估计回声和真实回声的欧式距离,那么反向的时候梯度肯定要对数学建模部分的卡尔曼滤波进行反向,我的建议是计算数学方法的凯尔曼滤波器系数和网络输出的滤波器系数的距离。或者固定数学建模部分,使用最后的loss。
那作者怎么能训起来呢,请问你已经跑通了训练过程吗
from nkf-aec.
我自己写过,可以进行训练。作者还是很牛逼的。
from nkf-aec.
我自己写过,可以进行训练。作者还是很牛逼的。
你也很牛逼,实测效果怎样呢
from nkf-aec.
尴尬咯,我的实验结果是,基础的数学建模凯尔曼滤波 < 网络的凯尔曼滤波 < 状态因子优化的数学建模凯尔曼滤波
from nkf-aec.
论文里一句话"After one forward pass" 估计回声hat_h和消除后的信号hat_S 可以得到, 然后用真实回声和估计回声做loss。 这里面的 one forward pass 难道是一个时刻t? 每一帧算一次loss? 然后更新梯度?
from nkf-aec.
我查到了作者之前关于这篇论文的报告 https://www.livevideostack.cn/video/
from nkf-aec.
我查到了作者之前关于这篇论文的报告 https://www.livevideostack.cn/video/
你好,请问一下你成功复现出了模型效果吗
from nkf-aec.
我自己写过,可以进行训练。作者还是很牛逼的。
您好,可以参考一下您的训练代码吗?我自己写的经常出现nan的情况,感谢!
from nkf-aec.
我查到了作者之前关于这篇论文的报告 https://www.livevideostack.cn/video/
你好,请问一下你成功复现出了模型效果吗
你好,请问你有进展吗?看起来这个网络计算量并不小,它将网络作用于每个频点。
from nkf-aec.
尴尬咯,我的实验结果是,基础的数学建模凯尔曼滤波 < 网络的凯尔曼滤波 < 状态因子优化的数学建模凯尔曼滤波
请教下,状态因子优化的数学建模卡尔曼滤波是怎么做的?有相关论文没
from nkf-aec.
Related Issues (20)
- waiting for the paper HOT 1
- Potential extension to fullband HOT 1
- BAD RESULT HOT 1
- 有关用自己数据测试 HOT 2
- 与kalman似乎没太大关系?
- 在ICASSP 2021 AEC Challenge blind_test_set clean的测试结果与论文不一致 HOT 5
- 如何应对滤波器发散?如何判断收敛情况? HOT 4
- 请教下作者,训练过程中所使用的线性系统的响应长度和幅度缩放是怎么设置的?多谢
- 关于损失函数计算参数设置的问题
- TRAIN 模型请教 HOT 4
- I have a question for the Experimental Setup. HOT 1
- tensorflow实现
- More exact model for frequency-domain forward pass HOT 1
- How to solve 'nan' loss in training? HOT 14
- Details in network training HOT 10
- Some problems on real sequences. HOT 2
- why put self.kg_net.init_hidden in the NKF forward function? HOT 4
- I found that the cost of NKF is a little bit huge. HOT 1
- Question about the training dataset HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nkf-aec.