search

nilmtk / nilmtk-contrib

Apache License 2.0
114 stars 59 forks source link

nilmtk-contrib installation failed #64

Open cemik1 opened 2 years ago

cemik1 commented 2 years ago

I can not install nilmtk-contrib package. Installed libraries and listing below. What could be a problem? System - win10 64-bit conda 4.11.0

packages in environment at C:\Users\710_004733\Anaconda3\envs\nilmtk-env:

Name Version Build Channel

nilmtk 0.4.3 py_0 nilmtk scikit-learn 1.0.2 py38hb60ee80_0 conda-forge keras 2.4.3 pyhd8ed1ab_0 conda-forge keras-applications 1.0.8 py_1 conda-forge keras-preprocessing 1.1.2 pyhd8ed1ab_0 conda-forge cvxpy 1.1.18 py38haa244fe_0 conda-forge cvxpy-base 1.1.18 py38h5d928e2_0 conda-forge

(nilmtk-env) C:\Users\710_004733>conda install -c conda-forge -c nilmtk nilmtk-contrib Collecting package metadata (current_repodata.json): done Solving environment: failed with initial frozen solve. Retrying with flexible solve. Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source. Collecting package metadata (repodata.json): done Solving environment: failed with initial frozen solve. Retrying with flexible solve. Solving environment: \ Found conflicts! Looking for incompatible packages. This can take several minutes. Press CTRL-C to abort.| failed

UnsatisfiableError: The following specifications were found to be incompatible with each other:

Output in format: Requested package -> Available versions

(nilmtk-env) C:\Users\710_004733>

rpolea commented 2 years ago

Ok @cemik1 I think I have just managed to get this to work by creating the dedicated environment within conda and installing nilmtk and nilmtk-contrib at the same time. I believe conda finds the appropriate installs to use when calling both and in the new environment there shouldn't be any conflicts. I was having issues before as I did nilmtk first and then tried to install nilmtk-contrib into the same environment.

Just to say I used Anaconda for Windows.

conda create -n nilmtk-test -c conda-forge -c nilmtk nilmtk-contrib

I did find there was an issue when testing the imports of the neural nets like Seq2Seq as it said tensorflow wasn't installed/found. I installed tensorflow within the environment but it gave me an error, however it seems to accept the import now.

Will update if I find that it still doesn't work.

paulfrank1997 commented 2 years ago

@rpolea Can I ask you about what version of tensorflow, h5py and keras you install? The original nilmtk-contrib does not contain tensorflow. But after I tried to install it by myself, I still got errors. So I was wondering whether that was caused by version problems.