Comments (3)
您好!
感谢对我们工作的关注。
效果偏低可能是因为没有用pretrain文件夹中的yaml配置文件,替换原始的config.yaml文件。
原始的config.yaml只在dev集上训练,bearing预训练参数是在dev+eval两个数据集上训练的。
输入样本会根据数据集的均值和方差进行归一化,使用错误的config.yaml,会只使用dev集的统计量进行归一化,导致结果变差。
祝好!
from aegan-ad.
非常感谢您百忙之中的回复!
我们确定使用了bearing_cfg.yaml中的参数设置,只在dataset_dir处做了改变。同时又观察了spec\deval\bearing文件夹中生成的train_scale_mel_128_2048_512_1.npy文件,显示其中的均值和方差分别是[ 9.994418 -60.24845 ],不知道是不是因为这两个数值不对导致了结果有所偏差。
另外,我们又对fan数据集进行了测试,其中npy文件的均值和方差分别是[ 22.920975 -66.271965],同时我们又观察到了偏高的best hmean
========= Test Machine Type: fan =========
============== TEST DATASET GENERATOR ==============
============== TRAIN DATASET GENERATOR ==============
=> Recorded best hmean: 0.6583
=> Detection on dev test set
100%|██████████| 600/600 [00:42<00:00, 14.14it/s]
=> Best metric: G_z_cos_sum; Best hmean: 0.6724
from aegan-ad.
更正一下,归一化方式实际为MinMax归一化为[0,1],而非减均值除标准差的归一化。
2种机器的归一化系数都存在差异。bearing的归一化系数为[9.994418, -57.940884],fan的归一化系数为[22.920979, -64.80351]。
test.py已更新,原代码中若不先运行train.py就运行test.py时,会缺少归一化系数文件,之前的问题可能出在这里。
可以考虑更新代码,或先运行train.py获得新归一化系数,再比较是否一致。
若不一致,应该是本地数据集的问题。
from aegan-ad.
Related Issues (13)
- 看了您《基于GAN的无监督机器音频异常检测与定位》的报告后有几个问题想请教您 HOT 2
- 对一个音频进行推理 HOT 1
- 运行代码后效果不是很理想 HOT 5
- 请问一下20的数据集您使用的是什么指标。 HOT 1
- 有一些关于代码的问题想请教您 HOT 2
- 我想请教一下您这篇论文训练的时候用了附加训练集吗?测试的时候用的是开发集的test数据吗? HOT 1
- 您好,我在跑22年的代码时,出现了莫名的报错 HOT 5
- 关于代码运行速度的问题想请教下您 HOT 2
- 关于代码的一些问题 HOT 10
- 请教代码相关问题 HOT 2
- 请教数据集划分问题 HOT 5
- 流式识别 HOT 1
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 aegan-ad.