run error

[Littlepuppet]

Hello, after I configured the file according to your requirements, I ran the code and found that the following error was reported.It would be a big help if anyone can guide a way! Thanks in Advance :)

[Ben-Yee]

Hello, after I configured the file according to your requirements, I ran the code and found that the following error was reported.It would be a big help if anyone can guide a way! Thanks in Advance :)

Which version of tensorflow are you using?I am using tf1.15.0, and I don`t have the same problem as yours

[Littlepuppet]

Hello, after I configured the file according to your requirements, I ran the code and found that the following error was reported.It would be a big help if anyone can guide a way! Thanks in Advance :)

Which version of tensorflow are you using?I am using tf1.15.0, and I don`t have the same problem as yours

I use the version tf 1.14.0 given in your requirements.txt.

[Littlepuppet]

I also find the version of tensorboard cannot match both the version of tf1.14.0 and tf_gpu 2.0.0 in therequirements.txt.

[ETSSmartRes]

Hello,

I'm working on your issue. I modified my env to try to replicate the problem. If you want to use Tensorflow 2+, you should use TensorFlow 2.2.0. I tried with a more recent version but I got the same error and didn't find a solution so far.

This is my suggested solution:

Create a new env with this new requirement file:

name: GHVN_env_36
channels:
  - conda-forge
  - defaults
dependencies:
  - _libgcc_mutex=0.1
  - _openmp_mutex=4.5
  - _tflow_select=2.1.0
  - abseil-cpp=20210324.2
  - absl-py=1.0.0
  - aiohttp=3.7.4.post0
  - astor=0.8.1
  - astunparse=1.6.3
  - async-timeout=3.0.1
  - attrs=21.4.0
  - blinker=1.4
  - brotlipy=0.7.0
  - c-ares=1.18.1
  - ca-certificates=2021.10.8
  - cachetools=4.2.4
  - certifi=2021.5.30
  - cffi=1.14.6
  - chardet=4.0.0
  - charset-normalizer=2.0.9
  - click=8.0.1
  - cryptography=35.0.0
  - cudatoolkit=10.1.243
  - cudnn=7.6.5.32
  - cupti=10.1.168
  - dataclasses=0.8
  - gast=0.3.3
  - giflib=5.2.1
  - google-auth=1.35.0
  - google-auth-oauthlib=0.4.6
  - google-pasta=0.2.0
  - grpc-cpp=1.37.1
  - grpcio=1.37.1
  - h5py=2.10.0
  - hdf5=1.10.6
  - icu=68.2
  - idna=3.1
  - idna_ssl=1.1.0
  - importlib-metadata=4.8.1
  - joblib=1.1.0
  - jpeg=9d
  - keras-preprocessing=1.1.2
  - krb5=1.19.2
  - ld_impl_linux-64=2.36.1
  - libblas=3.9.0
  - libcblas=3.9.0
  - libcurl=7.80.0
  - libedit=3.1.20191231
  - libev=4.33
  - libffi=3.4.2
  - libgcc-ng=11.2.0
  - libgfortran-ng=11.2.0
  - libgfortran5=11.2.0
  - libgomp=11.2.0
  - liblapack=3.9.0
  - libnghttp2=1.43.0
  - libnsl=2.0.0
  - libopenblas=0.3.18
  - libpng=1.6.37
  - libprotobuf=3.15.8
  - libssh2=1.10.0
  - libstdcxx-ng=11.2.0
  - libzlib=1.2.11
  - markdown=3.3.6
  - multidict=5.2.0
  - ncurses=6.2
  - numpy=1.19.5
  - oauthlib=3.1.1
  - openssl=1.1.1l
  - opt_einsum=3.3.0
  - pandas=1.1.5
  - pip=21.3.1
  - protobuf=3.15.8
  - pyasn1=0.4.8
  - pyasn1-modules=0.2.7
  - pycparser=2.21
  - pyjwt=2.3.0
  - pyopenssl=21.0.0
  - pysocks=1.7.1
  - python=3.6.15
  - python-dateutil=2.8.2
  - python-flatbuffers=1.12
  - python_abi=3.6
  - pytz=2021.3
  - pyu2f=0.1.5
  - re2=2021.08.01
  - readline=8.1
  - requests=2.26.0
  - requests-oauthlib=1.3.0
  - rsa=4.8
  - scikit-learn=0.24.2
  - scipy=1.5.3
  - setuptools=49.6.0
  - six=1.16.0
  - snappy=1.1.8
  - sqlite=3.37.0
  - tensorboard=2.4.1
  - tensorboard-plugin-wit=1.8.0
  - tensorflow=2.2.0
  - tensorflow-base=2.2.0
  - tensorflow-estimator=2.4.0
  - tensorflow-gpu=2.2.0
  - termcolor=1.1.0
  - threadpoolctl=3.0.0
  - tk=8.6.11
  - typing-extensions=4.0.1
  - typing_extensions=4.0.1
  - urllib3=1.26.7
  - werkzeug=2.0.1
  - wheel=0.37.1
  - wrapt=1.13.1
  - xz=5.2.5
  - yarl=1.6.3
  - zipp=3.6.0
  - zlib=1.2.11

Furthermore, you will have to modify the model by doing it for the "config == "fixe_filter" in the file NILM_function.py

replace the line:

eps = tf.keras.Input(tensor=K.random_normal(shape=(K.shape(x)[0], latent_dim)), name="eps")

with:

def get_eps(x, latent_dim):
    eps = K.random_normal(shape=(K.shape(x)[0], latent_dim))
    return eps

eps = tf.keras.layers.Lambda(get_eps, arguments={"latent_dim": latent_dim})(x)

and change:

model = tf.keras.Model(inputs=[x, eps], outputs=[x_pred])

for

model = tf.keras.Model(inputs=[x], outputs=[x_pred])

Finally, you have to add the following line after imports in NILM_disaggregation.py and NILM_test.py.

tf.compat.v1.disable_eager_execution()

Let me know if this solution works, I will update the files in GitHub.

Thanks,

Antoine

[Littlepuppet]

No need to modify the environment. I found that after modifying the code you mentioned, the model can run successfully. Thank you very much for your guidance.