Giter Club home page Giter Club logo

bhafsa / deep-nilmtk-v1 Goto Github PK

View Code? Open in Web Editor NEW
24.0 24.0 7.0 9.43 MB

Deep-NILMtk is an open source package designed specifically for deep models applied to solve NILM. It implements the general NILM pipeline independently of the deep learning backend. In its current version the toolkit considers two of the most popular deep learning pipelines. The training and testing phases are fully compatible with NILMtk. Several

Python 2.96% Jupyter Notebook 97.04%

deep-nilmtk-v1's Introduction

Hi there 👋

📖 About ME

  • 💼 ML enthousiast continiously conducting research about their applications

  • 📫 [email protected]

⬆ Research Interest

  • 1️⃣ Deep learning for time series.
  • 2️⃣ Anomaly detection in human behavior.
  • 3️⃣ ML applications in wearable devices and smart homes.
  • 4️⃣ Smart cities and digital twins

deep-nilmtk-v1's People

Contributors

bhafsa avatar dbrtii avatar sambaiga avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar

Forkers

hilabgu klerings marieltinaco stephenzwj anamaria-cusco omidreza-amrollahi massawe14

deep-nilmtk-v1's Issues

Colab template doesn't take installation

The template on colab doesn't support the updated python version. After downgrading the python version to 3.7, still all the pakages doesn't take installation. Not able to run on colab, hoping to hear from you on your implementation.

Make tensorflow dependency optional, remove keras dependency

When running this code line

from deep_nilmtk.disaggregator import NILMExperiment

I get an error that keras is missing. Both tensorflow and keras are not specified in requirements.txt

ModuleNotFoundError                       Traceback (most recent call last)
Cell In[1], line 1
----> 1 from deep_nilmtk.disaggregator import NILMExperiment

File c:\Users\admin\miniconda3\envs\energy_env2\lib\site-packages\deep_nilmtk\__init__.py:1
----> 1 from .config import *
      2 from .data import *
      3 from .disaggregator import *

File c:\Users\admin\miniconda3\envs\energy_env2\lib\site-packages\deep_nilmtk\config\__init__.py:2
      1 from .hparams import *
----> 2 from .models import __models__

File c:\Users\admin\miniconda3\envs\energy_env2\lib\site-packages\deep_nilmtk\config\models.py:1
----> 1 import deep_nilmtk.models.tensorflow as KerasModels
      2 import deep_nilmtk.models.pytorch as TorchModels
      4 import deep_nilmtk.data.loader.tensorflow as KerasLoader

File c:\Users\admin\miniconda3\envs\energy_env2\lib\site-packages\deep_nilmtk\models\__init__.py:2
      1 from .pytorch import *
----> 2 from .tensorflow import *

File c:\Users\admin\miniconda3\envs\energy_env2\lib\site-packages\deep_nilmtk\models\tensorflow\__init__.py:2
      1 from .seq2seq import *
...
----> 1 import keras
      2 import tensorflow as tf
      3 from tensorflow.keras.models import Sequential

ModuleNotFoundError: No module named 'keras'

As most models in this package are implemented in PyTorch anyway, I might make sense to make Tensorflow optional. I'd rather prefer to install just one backend...

The keras import could be replaced with tensorflow.keras

Found a typo for an import

In file deep_nilmtk/models/tensorflow/seq2point.py there is a typo in the first line.
tensorflow is misspelled as tesnorflow.

BR

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.