How to save a trained model (Estimator) and Load it back to test it with data in Tensorflow?

Question

I have this snippet, for my model

import pandas as pd
import tensorflow as tf
from tensorflow.contrib import learn
from tensorflow.contrib.learn.python import SKCompat
#Assume my dataset is using X['train'] as input and y['train'] as output

regressor = SKCompat(learn.Estimator(model_fn=lstm_model(TIMESTEPS, RNN_LAYERS, DENSE_LAYERS),model_dir=LOG_DIR))
validation_monitor = learn.monitors.ValidationMonitor(X['val'], y['val'], every_n_steps=PRINT_STEPS, early_stopping_rounds=1000)
regressor.fit(X['train'], y['train'],
              monitors=[validation_monitor],
              batch_size=BATCH_SIZE,
              steps=TRAINING_STEPS)

#After training this model I want to save it in a folder, so I can use the trained model for implementing in my algorithm to predict the output
#What is the correct format to use here to save my model in a folder called 'saved_model'
regressor.export_savedmodel('/saved_model/')

#I want to import it later in some other code, How can I import it?
#is there any function like import model from file?

How can I save this estimator? I tried finding some examples for tf.contrib.learn.Estimator.export_savedmodel, I did not have a success? Help Appreciated.

Answer 1

The function export_savedmodel requires the argument serving_input_receiver_fn, that is a function without arguments, which defines the input from the model and the predictor. Therefore, you must create your own serving_input_receiver_fn, where the model input type match with the model input in the training script, and the predictor input type match with the predictor input in the testing script. On the other hand, if you create a custom model, you must define the export_outputs, defined by the function tf.estimator.export.PredictOutput, which input is a dictionary that define the name that has to match with the name of the predictor output in the testing script.

For example:

TRAINING SCRIPT

def serving_input_receiver_fn():
    serialized_tf_example = tf.placeholder(dtype=tf.string, shape=[None], name='input_tensors')
    receiver_tensors      = {"predictor_inputs": serialized_tf_example}
    feature_spec          = {"words": tf.FixedLenFeature([25],tf.int64)}
    features              = tf.parse_example(serialized_tf_example, feature_spec)
    return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)

def estimator_spec_for_softmax_classification(logits, labels, mode):
    predicted_classes = tf.argmax(logits, 1)
    if (mode == tf.estimator.ModeKeys.PREDICT):
        export_outputs = {'predict_output': tf.estimator.export.PredictOutput({"pred_output_classes": predicted_classes, 'probabilities': tf.nn.softmax(logits)})}
        return tf.estimator.EstimatorSpec(mode=mode, predictions={'class': predicted_classes, 'prob': tf.nn.softmax(logits)}, export_outputs=export_outputs) # IMPORTANT!!!

    onehot_labels = tf.one_hot(labels, 31, 1, 0)
    loss          = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels, logits=logits)
    if (mode == tf.estimator.ModeKeys.TRAIN):
        optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
        train_op  = optimizer.minimize(loss, global_step=tf.train.get_global_step())
        return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)

    eval_metric_ops = {'accuracy': tf.metrics.accuracy(labels=labels, predictions=predicted_classes)}
    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)

def model_custom(features, labels, mode):
    bow_column           = tf.feature_column.categorical_column_with_identity("words", num_buckets=1000)
    bow_embedding_column = tf.feature_column.embedding_column(bow_column, dimension=50)   
    bow                  = tf.feature_column.input_layer(features, feature_columns=[bow_embedding_column])
    logits               = tf.layers.dense(bow, 31, activation=None)

    return estimator_spec_for_softmax_classification(logits=logits, labels=labels, mode=mode)

def main():
    # ...
    # preprocess-> features_train_set and labels_train_set
    # ...
    classifier     = tf.estimator.Estimator(model_fn = model_custom)
    train_input_fn = tf.estimator.inputs.numpy_input_fn(x={"words": features_train_set}, y=labels_train_set, batch_size=batch_size_param, num_epochs=None, shuffle=True)
    classifier.train(input_fn=train_input_fn, steps=100)

    full_model_dir = classifier.export_savedmodel(export_dir_base="C:/models/directory_base", serving_input_receiver_fn=serving_input_receiver_fn)

TESTING SCRIPT

def main():
    # ...
    # preprocess-> features_test_set
    # ...
    with tf.Session() as sess:
        tf.saved_model.loader.load(sess, [tf.saved_model.tag_constants.SERVING], full_model_dir)
        predictor   = tf.contrib.predictor.from_saved_model(full_model_dir)
        model_input = tf.train.Example(features=tf.train.Features( feature={"words": tf.train.Feature(int64_list=tf.train.Int64List(value=features_test_set)) })) 
        model_input = model_input.SerializeToString()
        output_dict = predictor({"predictor_inputs":[model_input]})
        y_predicted = output_dict["pred_output_classes"][0]

(Code tested in Python 3.6.3, Tensorflow 1.4.0)