Comments (2)
- calloss_magmse全带幅度谱loss最后是除以batch和频点维度,而分段幅度谱loss(calloss_magmse_subband)除的是batch和帧数,因为output_mag.shape[2]应该是T维度;
- 另外请问为什么不在T维度求平均呢?一般使用F.l1_loss的reduction直接用Mean就会在batch和F和T求平均,这样是对效果有啥影响吗?
主要是为了让各部分loss在数值量级上比较接近 方便设置权重
from uformer.
你好,关于sisnr loss, 我看你在loss文件里通过calloss调用了,我有个小疑问,我们训练的时候 要调用calloss还是sisnr?
假设是调用calloss的话,我会遇到一个问题就是,我传入的参数是[batch, 1, signal_size],会经常遇到 loss_total = loss_total / (output.shape[0] - zerocount) 除以0的问题。
假设直接调用sisnr,我传入参数是[batch, signal_size],会导致 t = torch.sum(x_zm * s_zm) * s_zm / (l2norm(s_zm)**2 + eps) 除以维度不统一。
from uformer.
Related Issues (11)
- 关于文章中参考模型参数量的问题 HOT 2
- Question about torch version HOT 1
- Input error when running uformer.py HOT 10
- DCCRN PLUS 的实现能开源吗 HOT 2
- Can the Uformer run in real time
- your work's torch version HOT 1
- Training HOT 1
- 关于训练过程出现的问题 HOT 2
- 关于复现网络出现的问题 HOT 5
- 参数量
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 uformer.