# ERROR \[Loadworkflowrunnable\] when I ran the Keras Network Learner 4:27 node **URL:** \ **Category:** KNIME Extensions\ **Tags:** deep-learning\ **Created:** [December 3, 2022, 7:30am UTC](https://forum.knime.com/t/error-loadworkflowrunnable-when-i-ran-the-keras-network-learner-4-27-node/50292 "2022-12-03T07:30:34Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![Haroon2001](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/h/bbce88/32.png) [@Haroon2001](https://forum.knime.com/u/Haroon2001)\ **Post date:** [December 3, 2022, 7:30am UTC](https://forum.knime.com/t/error-loadworkflowrunnable-when-i-ran-the-keras-network-learner-4-27-node/50292/1 "2022-12-03T07:30:34Z")
I am having this error when I the keras networl learner node in the following work flow: ![image](https://forum-cdn.knime.com/uploads/default/original/3X/c/5/c54df8532ac0a342d7443b32b2afd51dbc05fb63.png) and I have attached the KNIME log as well [Knime\_log\_workflow\_fail.txt](https://forum.knime.com/uploads/short-url/rY9akH1KiCwL5Nha89xecW5t34U.txt) (130.6 KB) ---
**Author:** ![mlauber71](https://forum-cdn.knime.com/user_avatar/forum.knime.com/mlauber71/32/73590_2.png) [@mlauber71](https://forum.knime.com/u/mlauber71)\ **Post date:** [December 3, 2022, 10:36am UTC](https://forum.knime.com/t/error-loadworkflowrunnable-when-i-ran-the-keras-network-learner-4-27-node/50292/2 "2022-12-03T10:36:34Z")
@Haroon2001 from the log it is difficult to determine what the problem might be. I see two things: - the configuration of the Python / Deep Learning environment itself - the configuration / setup of the data and network if this fits the task Maybe you could try and run this example with the propagation node for Windows and Keras and see if this does work. Next step would be to check the setup of your data > **[a simple deep learning network for binary classification using the KNIME...](https://hub.knime.com/mlauber71/spaces/Public/latest/kn_example_deeplearning_keras_tensorflow_classification/kn_deeplearn_100_keras_basic~8pLvXVGL1hj7lXDh)** > > a simple deep learning network for binary classification using the KNIME Keras integration (with a Python environment propagation) Please note this example sho… I plan on releasing an article about KNIME and deep learning setup. To familiarise yourself with the concepts you could start with this one: > **[KNIME and Python — Setting up and managing Conda environments](https://medium.com/@mlxl/knime-and-python-setting-up-and-managing-conda-environments-2ac217792539)** > > TL;DR: install python/conda thru Miniforge, find and use specific YAML-files to manage an environment, tell KNIME and use their… ---
**Author:** ![mlauber71](https://forum-cdn.knime.com/user_avatar/forum.knime.com/mlauber71/32/73590_2.png) [@mlauber71](https://forum.knime.com/u/mlauber71)\ **Post date:** [December 3, 2022, 1:17pm UTC](https://forum.knime.com/t/error-loadworkflowrunnable-when-i-ran-the-keras-network-learner-4-27-node/50292/3 "2022-12-03T13:17:27Z")
@Haroon2001 the mentioned article is now online. You might want to take a look tough it might be a bit longer … > [@KNIME and Python — Setting up Deep Learning Environments for Keras and TensorFlow](https://forum.knime.com/t/knime-and-python-setting-up-deep-learning-environments-for-keras-and-tensorflow/50445): > > The follow-up to my article about [KNIME, Python and Conda](https://forum.knime.com/t/knime-and-python-setting-up-and-managing-conda-environments/49405) is now online dealing with the question of: KNIME and Python — Setting up Deep Learning Environments for Keras and TensorFlow ---
**Author:** ![Haroon2001](https://forum-cdn.knime.com/letter_avatar_proxy/v4/letter/h/bbce88/32.png) [@Haroon2001](https://forum.knime.com/u/Haroon2001)\ **Post date:** [December 5, 2022, 5:23am UTC](https://forum.knime.com/t/error-loadworkflowrunnable-when-i-ran-the-keras-network-learner-4-27-node/50292/4 "2022-12-05T05:23:01Z")
Alright so I have Python version 3.6.13 downloaded and I this my conda environment. \_tflow\_select 2.1.0 gpu abseil-cpp 20210324.2 hd77b12b\_0 absl-py 0.15.0 pyhd3eb1b0\_0 arrow-cpp 5.0.0 py36he9238d2\_8\_cpu conda-forge astor 0.8.1 py36haa95532\_0 attrs 21.4.0 pyhd3eb1b0\_0 aws-c-cal 0.5.11 he19cf47\_0 conda-forge aws-c-common 0.6.2 h2bbff1b\_0 aws-c-event-stream 0.2.7 h70e1b0c\_13 conda-forge aws-c-io 0.10.5 h2fe331c\_0 conda-forge aws-checksums 0.1.11 h1e232aa\_7 conda-forge aws-sdk-cpp 1.8.186 hb0612c5\_3 conda-forge backcall 0.2.0 pyhd3eb1b0\_0 blas 1.0 mkl bzip2 1.0.8 he774522\_0 c-ares 1.18.1 h2bbff1b\_0 ca-certificates 2022.10.11 haa95532\_0 cairo 1.14.12 hf171d8a\_3 certifi 2021.5.30 py36haa95532\_0 colorama 0.4.4 pyhd3eb1b0\_0 coverage 5.5 py36h2bbff1b\_2 cudatoolkit 9.0 1 cudnn 7.6.5 cuda9.0\_0 cycler 0.11.0 pyhd3eb1b0\_0 cython 0.29.24 py36hd77b12b\_0 dataclasses 0.8 pyh4f3eec9\_6 decorator 5.1.1 pyhd3eb1b0\_0 freetype 2.10.4 hd328e21\_0 gast 0.5.3 pyhd3eb1b0\_0 gflags 2.2.2 ha925a31\_0 glog 0.5.0 hd77b12b\_0 grpc-cpp 1.40.0 h2431d41\_1 conda-forge grpcio 1.36.1 py36hc60d5dd\_1 h5py 2.8.0 py36hf7173ca\_0 hdf5 1.8.18 vc14h7a021fe\_0 [vc14] anaconda icc\_rt 2022.1.0 h6049295\_2 icu 58.2 vc14hc45fdbb\_0 [vc14] anaconda importlib-metadata 4.8.1 py36haa95532\_0 importlib\_metadata 4.8.1 hd3eb1b0\_0 intel-openmp 2022.1.0 h59b6b97\_3788 ipython 7.1.1 py36h39e3cac\_0 ipython\_genutils 0.2.0 pyhd3eb1b0\_1 jedi 0.13.3 py36\_0 jpeg 9b vc14h4d7706e\_1 [vc14] anaconda jpype1 0.6.3 py36h79cbd7a\_1001 conda-forge jsonschema 3.2.0 pyhd3eb1b0\_2 jupyter\_core 4.8.1 py36haa95532\_0 keras 2.2.4 0 keras-applications 1.0.8 py\_1 keras-base 2.2.4 py36\_0 keras-preprocessing 1.1.2 pyhd3eb1b0\_0 kiwisolver 1.3.1 py36hd77b12b\_0 lerc 3.0 hd77b12b\_0 libbrotlicommon 1.0.9 h2bbff1b\_7 libbrotlidec 1.0.9 h2bbff1b\_7 libbrotlienc 1.0.9 h2bbff1b\_7 libcurl 7.82.0 h86230a5\_0 libdeflate 1.8 h2bbff1b\_5 libpng 1.6.37 h2a8f88b\_0 libprotobuf 3.18.0 h7755175\_1 conda-forge libssh2 1.10.0 hcd4344a\_0 libthrift 0.15.0 he1d8c1a\_0 libtiff 4.4.0 h8a3f274\_2 libutf8proc 2.6.1 h2bbff1b\_0 lz4-c 1.9.3 h2bbff1b\_1 markdown 3.3.4 py36haa95532\_0 matplotlib 3.0.3 py36hc8f65d3\_0 mkl 2020.2 256 mkl-service 2.3.0 py36h196d8e1\_0 mkl\_fft 1.2.0 py36h45dec08\_0 mkl\_random 1.1.1 py36h47e9c7a\_0 nbformat 4.4.0 py36\_0 numpy 1.16.1 py36h19fb1c0\_1 numpy-base 1.16.1 py36hc3f5095\_1 olefile 0.46 py36\_0 onnx 1.4.1 pypi\_0 pypi onnx-tf 1.2.1 pypi\_0 pypi openssl 1.1.1s h2bbff1b\_0 pandas 0.23.4 py36h830ac7b\_0 parquet-cpp 1.5.1 h34088ae\_4 parso 0.8.3 pyhd3eb1b0\_0 pickleshare 0.7.5 pyhd3eb1b0\_1003 pillow 5.3.0 py36hdc69c19\_0 pip 21.2.2 py36haa95532\_0 pixman 0.34.0 vc14h00fde18\_1 [vc14] anaconda prompt\_toolkit 2.0.10 py\_0 protobuf 3.18.0 py36he2d232f\_0 conda-forge py4j 0.10.9.2 pyhd3eb1b0\_0 pyarrow 5.0.0 py36h6720e24\_8\_cpu conda-forge pygments 2.11.2 pyhd3eb1b0\_0 pyparsing 3.0.4 pyhd3eb1b0\_0 pyqt 5.9.2 py36h6538335\_2 pyrsistent 0.17.3 py36he774522\_0 python 3.6.13 h3758d61\_0 python-dateutil 2.7.5 py36\_0 python\_abi 3.6 2\_cp36m conda-forge pytz 2021.3 pyhd3eb1b0\_0 pywin32 228 py36hbaba5e8\_1 pyyaml 5.3.1 py36he774522\_0 qt 5.9.7 vc14h73c81de\_0 [vc14] anaconda re2 2021.09.01 h0e60522\_0 conda-forge scipy 1.1.0 py36h29ff71c\_2 setuptools 58.0.4 py36haa95532\_0 sip 4.19.8 py36h6538335\_0 six 1.16.0 pyhd3eb1b0\_1 snappy 1.1.9 h6c2663c\_0 sqlite 3.40.0 h2bbff1b\_0 tensorboard 1.12.2 py36h33f27b4\_0 tensorflow 1.12.0 gpu\_py36ha5f9131\_0 tensorflow-base 1.12.0 gpu\_py36h6e53903\_0 tensorflow-gpu 1.12.0 h0d30ee6\_0 termcolor 1.1.0 py36haa95532\_1 tk 8.6.12 h2bbff1b\_0 tornado 6.1 py36h2bbff1b\_0 traitlets 4.3.3 py36haa95532\_0 typing 3.7.4.3 pypi\_0 pypi typing\_extensions 4.1.1 pyh06a4308\_0 vc 14.2 h21ff451\_1 vs2015\_runtime 14.27.29016 h5e58377\_2 wcwidth 0.2.5 pyhd3eb1b0\_0 werkzeug 2.0.3 pyhd3eb1b0\_0 wheel 0.37.1 pyhd3eb1b0\_0 wincertstore 0.2 py36h7fe50ca\_0 xz 5.2.6 h8cc25b3\_0 yaml 0.1.7 vc14h4cb57cf\_1 [vc14] anaconda zipp 3.6.0 pyhd3eb1b0\_0 zlib 1.2.11 vc14h1cdd9ab\_1 [vc14] anaconda zstd 1.5.0 h19a0ad4\_1 I would like you could help me figure what the issue is. I have read your article and I don’t think its a dependency issue. When I am running the workflow I am getting these warnings and errors: WARN Keras Network Learner 3:27 The number of rows of the input validation data table (99) is not a multiple of the selected validation batch size (10). Thus, the last batch of each validation phase will continue at the beginning of the validation data table after reaching its end. You can avoid that by adjusting the number of rows of the table or the batch size if desired. WARN Keras Network Learner 3:27 C:\Users\user\anaconda3\envs\py3\_knime\_dl\lib\site-packages\keras\engine\saving.py:292: UserWarning: No training configuration found in save file: the model was _not_ compiled. Compile it manually. ERROR Keras Network Learner 3:27 java.lang.Exception: Failed to receive message from Python or forward received message. Cause: Connection reset ERROR Keras Network Learner 3:27 Execute failed: An error occured during training of the Keras deep learning network. See log for details. I will also attached my log [Keras\_Network\_error\_5\_12\_22.txt](https://forum.knime.com/uploads/short-url/gPu8mQSFwBdgkgI1SaJmd7rhkWg.txt) (310.9 KB) ---
**Author:** ![mlauber71](https://forum-cdn.knime.com/user_avatar/forum.knime.com/mlauber71/32/73590_2.png) [@mlauber71](https://forum.knime.com/u/mlauber71)\ **Post date:** [December 5, 2022, 3:25pm UTC](https://forum.knime.com/t/error-loadworkflowrunnable-when-i-ran-the-keras-network-learner-4-27-node/50292/5 "2022-12-05T15:25:04Z")
@Haroon2001 two things. First can you try to make this example work (download the [whole WF group](https://hub.knime.com/mlauber71/spaces/Public/latest/kn_example_deeplearning_keras_tensorflow_classification~G8jl-DTMCBqoxyB9/)) with the settings for windows: > **[Train a simple Multilayer Perceptron using TensorFlow 2 – mlauber71](https://hub.knime.com/mlauber71/spaces/Public/latest/kn_example_deeplearning_keras_tensorflow_classification/kn_deeplearn_050_tensorflow2_basic_mlp~0P1TaKHmebS4g8zv)** > > Train a simple Multilayer Perceptron using TensorFlow 2 for a binary classification This workflow shows how to train a simple multilayer perceptron for classif… Can you share your example or point to the hub. In the example you will note that the number of initial values is benign dynamically allocated. You might read about configurations in the resources mentioned at the end of my article (eg the book by KNIME: [Codeless Deep Learning with KNIME Book | KNIME](https://www.knime.com/codeless-deep-learning-book)). ---
**Author:** ![system](https://forum-cdn.knime.com/uploads/default/original/1X/ab3ccf34482a0329361734a18199390177204f15.png) [@system](https://forum.knime.com/u/system)\ **Post date:** [March 5, 2023, 3:25pm UTC](https://forum.knime.com/t/error-loadworkflowrunnable-when-i-ran-the-keras-network-learner-4-27-node/50292/6 "2023-03-05T15:25:35Z")
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.