save




https://stackoverflow.com/questions/33759623/tensorflow-how-to-save-restore-a-model




load saved_model directly in python and other languages: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/python/saved_model/

some minor savedModelBuilder example for a distributed tensorflow computation graph  https://github.com/tensorflow/serving/issues/363











Signature defs
https://www.tensorflow.org/api_docs/python/tf/saved_model/signature_constants
https://www.tensorflow.org/api_docs/python/tf/saved_model/signature_def_utils
https://www.tensorflow.org/api_docs/python/tf/saved_model/signature_def_utils/build_signature_def
https://www.tensorflow.org/api_docs/python/tf/saved_model/signature_def_utils/classification_signature_def
https://www.tensorflow.org/api_docs/python/tf/saved_model/signature_def_utils/predict_signature_def

Create SaveModelBuilder and use in google cloud

end to end tutorial using tensorflow serving

Saver / savedModelBuilder / with pre-built Docker https://towardsdatascience.com/deploy-tensorflow-models-9813b5a705d5


Pre-built docker images
https://medium.com/epigramai/tensorflow-serving-101-pt-1-a79726f7c103   Part 1                 -v mount dir
$ docker run -it -p 9000:9000 --name simple -v $(pwd)/models/:/models/ epigramai/model-server:light --port=9000 --model_name=simple --model_base_path=/models/simple_model    
mount shared drive   name of image to be downloaded 





tensroflow serving
https://www.tensorflow.org/serving/
https://www.tensorflow.org/serving/serving_advanced
https://www.tensorflow.org/serving/setup
https://www.tensorflow.org/serving/serving_basic
https://www.tensorflow.org/serving/serving_inception
https://github.com/tensorflow/serving/blob/master/tensorflow_serving/example/inception_client.py

youtube
https://www.youtube.com/watch?v=CSbfk9jXItc
https://gyang274.github.io/tensorflow-serving-tutorial/0x02b00.slim.inception.v4.html

tf-slim






deploy machine learning models tensorflow


Introductory
















Subpages (1): example
Comments