custom-ml-engine-deployment fails with latest depencies.

[sstteev]

https://github.com/pmservice/ai-openscale-tutorials/tree/master/applications/custom-ml-engine-containers

Error:

kubectl logs custom-ml-engine-deployment-67944fc864-97w85 
2020-03-20 13:43:42.738823: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer.so.6'; dlerror: libnvinfer.so.6: cannot open shared object file: No such file or directory
2020-03-20 13:43:42.739398: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer_plugin.so.6'; dlerror: libnvinfer_plugin.so.6: cannot open shared object file: No such file or directory
2020-03-20 13:43:42.739573: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:30] Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
20/03/20 13:43:47 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
Using TensorFlow backend.
/opt/conda/lib/python3.7/site-packages/sklearn/externals/joblib/__init__.py:15: FutureWarning: sklearn.externals.joblib is deprecated in 0.21 and will be removed in 0.23. Please import this functionality directly from joblib, which can be installed with: pip install joblib. If this warning is raised when loading pickled models, you may need to re-serialize those models with scikit-learn 0.21+.
  warnings.warn(msg, category=FutureWarning)
Traceback (most recent call last):
  File "/home/jovyan/run_server.py", line 239, in <module>
    load_resnet50_model()
  File "/home/jovyan/run_server.py", line 30, in load_resnet50_model
    with backend.get_session().graph.as_default() as g:
  File "/opt/conda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 379, in get_session
    '`get_session` is not available '
RuntimeError: `get_session` is not available when using TensorFlow 2.0.

I had success with the following requirements.

cfenv==0.5.3
Flask==1.0.2
watson-developer-cloud==1.3.5
gevent
requests
tensorflow==1.15.0
keras==2.2.5
ibmcloudenv
livereload
pillow
numpy
pyspark
pandas
scikit-learn==0.20.2