Inference from the saved model

[jageshmaharjan]

Based on the issue, I was able to save a model in pb format as well we previously saved a model in h5 format (Keras model).
I am trying to serve a model using TensorFlow servings, but the saved model doesn't have the signature definition, and hence couldn't do inference from the client.

Is there other way to do inference?

saved_model_cli show --dir /home/dsdev/gitrepo/ReferringRelationships/model/1/ --all
MetaGraphDef with tag-set: '' contains the following SignatureDefs:
Traceback (most recent call last):
  File "/data/anaconda/envs/py35/bin/saved_model_cli", line 11, in <module>
    sys.exit(main())
  File "/data/anaconda/envs/py35/lib/python3.5/site-packages/tensorflow/python/tools/saved_model_cli.py", line 910, in main
    args.func(args)
  File "/data/anaconda/envs/py35/lib/python3.5/site-packages/tensorflow/python/tools/saved_model_cli.py", line 611, in show
    _show_all(args.dir)
  File "/data/anaconda/envs/py35/lib/python3.5/site-packages/tensorflow/python/tools/saved_model_cli.py", line 199, in _show_all
    signature_def_map = get_signature_def_map(saved_model_dir, tag_set)
  File "/data/anaconda/envs/py35/lib/python3.5/site-packages/tensorflow/python/tools/saved_model_cli.py", line 243, in get_signature_def_map
    meta_graph = saved_model_utils.get_meta_graph_def(saved_model_dir, tag_set)
  File "/data/anaconda/envs/py35/lib/python3.5/site-packages/tensorflow/python/tools/saved_model_utils.py", line 49, in get_meta_graph_def
    ' could not be found in SavedModel')
RuntimeError: MetaGraphDef associated with tag-set  could not be found in SavedModel

and

dsdev@dsdev:/mnt/data/dataset-visualgenome/train$ tensorflow_model_server --port=8500 --rest_api_port=8501 --model_name=refrel --model_base_path=/home/dsdev/gitrepo/ReferringRelationships/model/
2019-11-12 07:09:14.359747: I tensorflow_serving/model_servers/server.cc:82] Building single TensorFlow model file config:  model_name: refrel model_base_path: /home/dsdev/gitrepo/ReferringRelationships/model/
2019-11-12 07:09:14.359974: I tensorflow_serving/model_servers/server_core.cc:461] Adding/updating models.
2019-11-12 07:09:14.359995: I tensorflow_serving/model_servers/server_core.cc:558]  (Re-)adding model: refrel
2019-11-12 07:09:14.460213: I tensorflow_serving/core/basic_manager.cc:739] Successfully reserved resources to load servable {name: refrel version: 1}
2019-11-12 07:09:14.460243: I tensorflow_serving/core/loader_harness.cc:66] Approving load for servable version {name: refrel version: 1}
2019-11-12 07:09:14.460261: I tensorflow_serving/core/loader_harness.cc:74] Loading servable version {name: refrel version: 1}
2019-11-12 07:09:14.460283: I external/org_tensorflow/tensorflow/contrib/session_bundle/bundle_shim.cc:363] Attempting to load native SavedModelBundle in bundle-shim from: /home/dsdev/gitrepo/ReferringRelationships/model/1
2019-11-12 07:09:14.460298: I external/org_tensorflow/tensorflow/cc/saved_model/reader.cc:31] Reading SavedModel from: /home/dsdev/gitrepo/ReferringRelationships/model/1
2019-11-12 07:09:14.533650: I external/org_tensorflow/tensorflow/cc/saved_model/reader.cc:54] Reading meta graph with tags { serve }
2019-11-12 07:09:14.538127: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:259] SavedModel load for tags { serve }; Status: fail. Took 77816 microseconds.
2019-11-12 07:09:14.538160: E tensorflow_serving/util/retrier.cc:37] Loading servable: {name: refrel version: 1} failed: Not found: Could not find meta graph def matching supplied tags: { serve }. To inspect available tag-sets in the SavedModel, please use the SavedModel CLI: `saved_model_cli`