search

OdysseasKr / neural-disaggregator

Code for NILM experiments using Neural Networks. Uses Keras/Tensorflow and the NILMTK.
MIT License
138 stars 57 forks source link

The result data is not correct #38

Open RengarWang opened 3 years ago

RengarWang commented 3 years ago

hi, i have run RNN-example.ipynb,but the data is not correct. my result is ============ Recall: 0.06080812748658777 ============ Precision: 0.7873688147161255 ============ Accuracy: 0.29049305213046556 ============ F1 Score: 0.11289725264136873 ============ Relative error in total energy: 0.7858544224150322 ============ Mean absolute error(in Watts): 19.859596349905722

but your result is ============ Recall: 0.997835349341 ============ Precision: 0.742378777703 ============ Accuracy: 0.741308963402 ============ F1 Score: 0.851357054837 ============ Relative error in total energy: 0.871686427835 ============ Mean absolute error(in Watts): 32.2338755931

I don't know what I did wrong.I ran it all according to your code.

RengarWang commented 3 years ago

By the way, I only use low_freq to redd.h5.

Ben-Yee commented 2 years ago

By the way, I only use low_freq to redd.h5.

Did you find out what`s wrong? I got the same issue

Ben-Yee commented 2 years ago

I think i know why.These four metrics is for classification.And frige's metadata didn't contain its on_power_threshold ,then it will be set to 10W by default.

DuoCaiXie commented 2 years ago

Hello, do you know how to solve this problem

DuoCaiXie commented 2 years ago

I think i know why.These four metrics is for classification.And frige's metadata didn't contain its on_power_threshold ,then it will be set to 10W by default.

Hello, do you know how to solve this problem

Ben-Yee commented 2 years ago

I think i know why.These four metrics is for classification.And frige's metadata didn't contain its on_power_threshold ,then it will be set to 10W by default.

Hello, do you know how to solve this problem

放弃了，代码有点久远了...你把Fridge的阈值设置为50W，应该会对。