zmjjmz

 # just the fn from model_store that takes:                                                
 model_builder = model_class(model_artifacts, **model_parameters)                          
 model_builder.build_model(inp_placeholder)
 # dict of tensors like {'softmax':softmax_layer, 'oov_code':oov_code}
 tensors = model_builder.give_outputs()                                                                                                               
                                                                                           
 if mode == tensorflow.estimator.ModeKeys.PREDICT:                                         
     return tensorflow.estimator.EstimatorSpec(                                            
         mode=mode,                                                                        
         predictions=tensors,                                                              

zmjjmz

import os

import psutil
import numpy
import tensorflow
from tensorflow.python.keras._impl import keras
from tensorflow.python.keras._impl.keras.backend import _GRAPH_LEARNING_PHASES


print("Tensorflow version: {0}".format(tensorflow.VERSION))

zmjjmz

from __future__ import division

import os

import numpy
import tensorflow as tf
from tensorflow.python.estimator.export.export_output import PredictOutput
from tensorflow.python.estimator.export.export import build_raw_serving_input_receiver_fn
from tensorflow.python.saved_model import signature_constants
from tensorflow.python import debug as tf_debug

zmjjmz

from __future__ import division

import os

import numpy
import tensorflow
from tensorflow.python.keras._impl import keras
from tensorflow.python.estimator.export.export_output import PredictOutput
from tensorflow.python.estimator.export.export import build_raw_serving_input_receiver_fn
from tensorflow.python.saved_model import signature_constants

zmjjmz

from __future__ import division

import urlparse
import os

import numpy
import boto3
import tensorflow
from tensorflow.python.keras._impl import keras
from tensorflow.python.estimator.export.export_output import PredictOutput

zmjjmz

from __future__ import division

import urlparse
import os

import numpy
import boto3
import tensorflow
from tensorflow.python.keras._impl import keras
from tensorflow.python.estimator.export.export_output import PredictOutput

zmjjmz

Using TensorFlow backend.
2017-12-20 14:04:22.144670: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
output from keras
[[[ 0.  0.  0.]
  [ 0.  0.  0.]
  [ 0.  0.  0.]
  [ 0.  0.  0.]
  [ 0.  0.  0.]]

 [[ 0.  0.  0.]

zmjjmz

Using TensorFlow backend.
2017-12-20 14:02:35.782187: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
output from keras
[[[ 0.  0.  0.]
  [ 0.  0.  0.]
  [ 0.  0.  0.]
  [ 0.  0.  0.]
  [ 0.  0.  0.]]

 [[ 0.  0.  0.]

zmjjmz

from  __future__ import division

import os
import sys
import subprocess
import time

import numpy as np
import tensorflow
from tensorflow.python.tools import inspect_checkpoint

zmjjmz

 class TokenizeLookupLayer(keras.layers.Layer):                                          
     """                                                                                 
     Layer that encapsulates the following:                                              
     - Tokenizing sentences by space (or given delimiter)                                
     - Looking up the words with a given vocabulary list / table                         
     - Resetting the shape of the above to be batch_size x pad_len (using dark magic)    
     # Input Shape                                         
       2D string tensor with shape `(batch_size, 1)`      
     # Output Shape                                        
       2D int32 tensor with shape `(batch_size, pad_len)`