OP_REQUIRES failed at ngraph_encapsulate_op.cc:418 : Internal: Error in compiling op_backend with error: Caught exception while compiling op_backend: Interpolate

[gargraghav]

Hi,

I installed ngraph while "building from source". Below are the versions I am currently using:

TensorFlow version:  1.15.2
nGraph bridge version: b'0.22.0-rc3'
nGraph version used for this build: b'0.28.0-rc.1+d2cd873'
TensorFlow version used for this build: v1.15.2-0-g5d80e1e8e6
CXX11_ABI flag used for this build: 1
nGraph bridge built with Grappler: False
nGraph bridge built with Variables and Optimizers Enablement: False
nGraph bridge built with Distributed Build: 0

I am getting this error while I use nGraph to simply classify an image using a frozen model as given in the nGraph official tutorials section.

2020-05-14 03:34:10.723836: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2400000000 Hz
2020-05-14 03:34:10.726438: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x4615940 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-05-14 03:34:10.726487: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-05-14 03:34:10.738302: I /home/raggarg/ngraph-bridge/ngraph_bridge/ngraph_rewrite_pass.cc:137] NGraph using backend: CPU
2020-05-14 03:34:10.829112: I /home/raggarg/ngraph-bridge/ngraph_bridge/ngraph_utils.cc:418] Serializing graph to: tf_function_error_ngraph_cluster_0.json

2020-05-14 03:34:10.829722: W tensorflow/core/framework/op_kernel.cc:1651] OP_REQUIRES failed at ngraph_encapsulate_op.cc:418 : Internal: Error in compiling op_backend with error: Caught exception while compiling op_backend: Interpolate
Traceback (most recent call last):
  File "/home/raggarg/ngraph-bridge/build_cmake/venv-tf-py3/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
    return fn(*args)
  File "/home/raggarg/ngraph-bridge/build_cmake/venv-tf-py3/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
    target_list, run_metadata)
  File "/home/raggarg/ngraph-bridge/build_cmake/venv-tf-py3/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InternalError: Error in compiling op_backend with error: Caught exception while compiling op_backend: Interpolate
         [[{{node ngraph_cluster_0}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "label_image.py", line 123, in <module>
    input_std=input_std)
  File "label_image.py", line 61, in read_tensor_from_image_file
    result = sess.run(normalized)
  File "/home/raggarg/ngraph-bridge/build_cmake/venv-tf-py3/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 956, in run
    run_metadata_ptr)
  File "/home/raggarg/ngraph-bridge/build_cmake/venv-tf-py3/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run
    feed_dict_tensor, options, run_metadata)
  File "/home/raggarg/ngraph-bridge/build_cmake/venv-tf-py3/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
    run_metadata)
  File "/home/raggarg/ngraph-bridge/build_cmake/venv-tf-py3/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Error in compiling op_backend with error: Caught exception while compiling op_backend: Interpolate
         [[{{node ngraph_cluster_0}}]]

Please help if anyone has any leads on it.