python - Can't run a command line prediction against a saved Tensorflow model -


i'm having trouble exporting , running simple example command line. example trains on random numbers 0-99 , labels values 0 if less 50, otherwise label 1. want able save model use later generate prediction against value entered via command line.

here rough guide using model saving , cli.

the environment tensorflow docker image.

here program - takes around 10 seconds run in environment.

"""create simple model can run cli.""" import math import os import numpy np os.environ['tf_cpp_min_log_level'] = '2'  # prevents compiler warnings import tensorflow tf  # pylint: disable=import-error   def generate_value_list(size=100):     """return array of random values 0-99."""     value_list = np.random.rand(size)     value_list = [math.trunc(x * 100) x in value_list]      return value_list   def generate_label_list(value_list):     """return array of labels passed values."""     label_list = [0 if x < 50 else 1 x in value_list]      return label_list   def input_fn():     """generate input training or evaluating."""     value_list = generate_value_list()     label_list = generate_label_list(value_list)     features = {"value_list": value_list}      return features, label_list   def main():     """execute main program."""     content = tf.feature_column.numeric_column(key='value_list')     columns = [content]     estimator = tf.estimator.linearclassifier(         feature_columns=columns,         optimizer=tf.train.ftrloptimizer(             learning_rate=0.1,             l1_regularization_strength=0.001))      estimator.train(input_fn=input_fn, steps=500)     result = estimator.evaluate(input_fn=input_fn, steps=5)     print result      feature_spec = tf.feature_column.make_parse_example_spec(columns)     export_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)     estimator.export_savedmodel('/notebooks/model', export_input_fn)   if __name__ == "__main__":     main()

after running program have model saved in model directory. see model interface, run following command:

saved_model_cli show --dir /notebooks/model/1505225506 --all

and this:

metagraphdef tag-set: 'serve' contains following signaturedefs:  signature_def['none']: given savedmodel signaturedef contains following input(s): inputs['inputs'] tensor_info:     dtype: dt_string     shape: (-1)     name: input_example_tensor:0 given savedmodel signaturedef contains following output(s): outputs['classes'] tensor_info:     dtype: dt_string     shape: (-1, 2)     name: linear/head/tile:0 outputs['scores'] tensor_info:     dtype: dt_float     shape: (-1, 2)     name: linear/head/predictions/probabilities:0 method name is: tensorflow/serving/classify  signature_def['classification']: given savedmodel signaturedef contains following input(s): inputs['inputs'] tensor_info:     dtype: dt_string     shape: (-1)     name: input_example_tensor:0 given savedmodel signaturedef contains following output(s): outputs['classes'] tensor_info:     dtype: dt_string     shape: (-1, 2)     name: linear/head/tile:0 outputs['scores'] tensor_info:     dtype: dt_float     shape: (-1, 2)     name: linear/head/predictions/probabilities:0 method name is: tensorflow/serving/classify  signature_def['regression']: given savedmodel signaturedef contains following input(s): inputs['inputs'] tensor_info:     dtype: dt_string     shape: (-1)     name: input_example_tensor:0 given savedmodel signaturedef contains following output(s): outputs['outputs'] tensor_info:     dtype: dt_float     shape: (-1, 1)     name: linear/head/predictions/logistic:0 method name is: tensorflow/serving/regress  signature_def['serving_default']: given savedmodel signaturedef contains following input(s): inputs['inputs'] tensor_info:     dtype: dt_string     shape: (-1)     name: input_example_tensor:0 given savedmodel signaturedef contains following output(s): outputs['classes'] tensor_info:     dtype: dt_string     shape: (-1, 2)     name: linear/head/tile:0 outputs['scores'] tensor_info:     dtype: dt_float     shape: (-1, 2)     name: linear/head/predictions/probabilities:0 method name is: tensorflow/serving/classify

next run prediction on number input:

saved_model_cli run --dir /notebooks/model/1505225506 --tag_set serve --signature_def serving_default --input_exprs 'inputs=[32]'

and this:

traceback (most recent call last):   file "/usr/local/bin/saved_model_cli", line 11, in <module>     sys.exit(main())   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/tools/saved_model_cli.py", line 649, in main     args.func(args)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/tools/saved_model_cli.py", line 529, in run     args.overwrite, tf_debug=args.tf_debug)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/tools/saved_model_cli.py", line 298, in run_saved_model_with_feed_dict     outputs = sess.run(output_tensor_names_sorted, feed_dict=inputs_feed_dict)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 895, in run     run_metadata_ptr)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1124, in _run     feed_dict_tensor, options, run_metadata)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1321, in _do_run     options, run_metadata)   file "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1340, in _do_call     raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.internalerror: unable element feed bytes.

i've tried many variations input model , 1 seems furthest in code before erroring out.

any ideas i'm doing wrong? there better way accomplish similar?


Comments

Post a Comment

Popular posts from this blog

neo4j - finding mutual friends in a cypher statement starting with three or more persons -

Image
i trying build cypher statement neo4j know 2-n starting nodes name , need find node (if any) can reached of starting nodes. at first tought similar "mutual friend" situation handled (start1)-[*..2]->(main)<-[*..2]-(start2) in case have more 2 starting points around 6 know name. so puzzled how can include third, fourth , on node cypher able find commmon root amongst them. in above example neo4j website need path starting 'dilshad', 'becky' , 'cesar' check if have common friend (anders) excluding 'filipa' , 'emil' not friends of three. so far create statement programmatically looks like match (start1 {name:'person1'}), (start2 {name:'person2'}), (start3 {name: 'person3'}), (main) (start1)-[*..2]->(main) , (start2)-[*..2]->(main) , (start3)-[*..2]->(main) return distinct main but wondering if there more elegant / efficient way in cypher possibly use list of names parameter ...
Read more

php - How to remove letter in front of the word laravel -

Image
based on picture above result of var_dump() , dd() of same variable ,when var_dump() , apostrophe (') symbol in black diamond of question mark , when dd() same variable , apostrophe can seen letter 'b' appear in front of words what want can me result : loreal's sdn bhd and @ same time want remove special character ( excluding these 4 symbols (-) ,(_) ,('),(,) ) simply escape special character resolve issue. mysqli_real_escape_string resolve issue. $name = mysqli_real_escape_string($request()->user); or use addslashes function() $name = addslashes($request()->user);
Read more

minify - Minimizing css files -

i want know how css files can minimized. currently, using external sites css minifier compress css files. however, after removing whitespaces, comments, etc, file sizes reduced 10-15%. how frameworks bootstrap manage make minimized versions kilobytes. as example, css is: body { background-color: #ff0; } the reduction goes 28 bytes 22 bytes other css files have lot more characters still smaller this. actually minifying code means it's remove thing code white space characters new line characters comments block delimiters it reduces amount of code has transferred on web , speed site load fastly.but unreadable format.
Read more