hub
hub copied to clipboard
tensorflow
Bug: REST API available for multilingual_universal_encoder
What happened?
I am trying to use the model from: hub/examples/colab/cross_lingual_similarity_with_tf_hub_multilingual_universal_encoder.ipynb
I intend to use the saved model through REST, but do not know the required Inputs. Is there a documentation for the REST API which is available for the multilingual_universal_encoder?
Many Thanks
Relevant code
saved_model_cli show --dir /home/udot_user_01/serving/saved_models/use-multilingual/3 --all
Relevant log output
I have tried to use the `saved_model_cli` but I get the following error:
2022-06-07 11:55:26.082177: I tensorflow/core/util/util.cc:169] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2022-06-07 11:55:27.027213: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2022-06-07 11:55:27.027290: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:
signature_def['__saved_model_init_op']:
The given SavedModel SignatureDef contains the following input(s):
The given SavedModel SignatureDef contains the following output(s):
outputs['__saved_model_init_op'] tensor_info:
dtype: DT_INVALID
shape: unknown_rank
name: NoOp
Method name is:
signature_def['serving_default']:
The given SavedModel SignatureDef contains the following input(s):
inputs['inputs'] tensor_info:
dtype: DT_STRING
shape: (-1)
name: serving_default_inputs:0
The given SavedModel SignatureDef contains the following output(s):
outputs['outputs'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 512)
name: StatefulPartitionedCall:0
Method name is: tensorflow/serving/predict
Traceback (most recent call last):
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/framework/ops.py", line 4155, in _get_op_def
return self._op_def_cache[type]
KeyError: 'SentencepieceOp'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py", line 912, in load_partial
loader = Loader(object_graph_proto, saved_model_proto, export_dir,
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py", line 151, in __init__
function_deserialization.load_function_def_library(
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/saved_model/function_deserialization.py", line 409, in load_function_def_library
func_graph = function_def_lib.function_def_to_graph(
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/framework/function_def_to_graph.py", line 82, in function_def_to_graph
graph_def, nested_to_flat_tensor_name = function_def_to_graph_def(
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/framework/function_def_to_graph.py", line 252, in function_def_to_graph_def
op_def = default_graph._get_op_def(node_def.op) # pylint: disable=protected-access
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/framework/ops.py", line 4159, in _get_op_def
pywrap_tf_session.TF_GraphGetOpDef(self._c_graph, compat.as_bytes(type),
tensorflow.python.framework.errors_impl.NotFoundError: Op type not registered 'SentencepieceOp' in binary running on 3jw7.l.time4vps.cloud. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/udot_user_01/miniconda3/bin/saved_model_cli", line 8, in <module>
sys.exit(main())
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/tools/saved_model_cli.py", line 1285, in main
args.func(args)
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/tools/saved_model_cli.py", line 747, in show
_show_all(args.dir)
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/tools/saved_model_cli.py", line 314, in _show_all
_show_defined_functions(saved_model_dir)
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/tools/saved_model_cli.py", line 192, in _show_defined_functions
trackable_object = load.load(saved_model_dir)
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py", line 782, in load
result = load_partial(export_dir, None, tags, options)["root"]
File "/home/udot_user_01/miniconda3/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py", line 915, in load_partial
raise FileNotFoundError(
FileNotFoundError: Op type not registered 'SentencepieceOp' in binary running on 3jw7.l.time4vps.cloud. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
You may be trying to load on a different device from the computational device. Consider setting the `experimental_io_device` option in `tf.saved_model.LoadOptions` to the io_device such as '/job:localhost'.
### tensorflow_hub Version
0.12.0 (latest stable release)
### TensorFlow Version
2.8 (latest stable release)
### Other libraries
_No response_
### Python Version
3.x
### OS
Linux
