yueeeeeeee / bert4nilm Goto Github PK
View Code? Open in Web Editor NEW[NILM@SenSys 2020] PyTorch Implementation of BERT4NILM: A Bidirectional Transformer Model for Non-Intrusive Load Monitoring
[NILM@SenSys 2020] PyTorch Implementation of BERT4NILM: A Bidirectional Transformer Model for Non-Intrusive Load Monitoring
It's not clear how to obtain params claimed in the paper specifically for UK-DALE, kettle
the paper promises MAE = 6.82
but under default settings for UK-DALE I am getting MAE=22
and also much worse F1....
Hi @Yueeeeeeee ,
I have one doubt regarding the minimum on and minimum off duration that you have used in the utils.py. I believe it is the total num of points that is in minimum on and off duration right and it will depend in sampling rate can you please help me with this.
Also i am trying out the same model for dataport dataset with sampling=15min, can you please help me how i decide the lambda parameter for appliance like.. air conditioner and fridge as well as minimum on and off duration..
the bert is pre-train , so it need to fine-tune after ?
Hello.How to plot the energy consumption cueve of test results using Python?
While reproducing the issue, I encountered the following error. It appears that when processing house 1, you are assigning house_data to entire_data. Later, when attempting to append to it, an error occurs. I suspect that concatenation might be a better approach here. Here's an improved explanation:
When processing data for house 1, you initialize entire_data with house_data. Later, when you try to append new data to entire_data, an error occurs because the append method does not modify the original data structure in place as expected. Instead, it's better to use concatenation to merge the data.
entire_data = entire_data.append(house_data, ignore_index=True)
^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'DataFrame' object has no attribute 'append'. Did you mean: '_append'?
if house_id == self.house_indicies[0]:
entire_data = house_data
else:
entire_data = entire_data.append(
house_data, ignore_index=True)
entire_data = entire_data.dropna().copy()
entire_data = entire_data[entire_data['aggregate'] > 0]
entire_data[entire_data < 5] = 0
entire_data = entire_data.clip(
[0] * len(entire_data.columns), self.cutoff, axis=1)
return entire_data.values[:, 0], entire_data.values[:, 1:]
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.