Tensorflow: How to save a 'DNNRegressorV2' model? python

Question

I run into problem when trying to save a trained model, I've tried:

model.save('~/Desktop/models/')

but it gave me an error AttributeError: 'DNNRegressorV2' object has no attribute 'save'

I have also tried:

tf.saved_model.save(model, mobilenet_save_path)

but it gave me an error ValueError: Expected a Trackable object for export, got <tensorflow_estimator.python.estimator.canned.dnn.DNNRegressorV2 object at 0x111cc4b70>.

Any idea?

>type(model)
<class 'tensorflow_estimator.python.estimator.canned.dnn.DNNRegressorV2'>

question from:https://stackoverflow.com/questions/65901303/tensorflow-how-to-save-a-dnnregressorv2-model-python

Answer 1

To save an Estimator you need to create a serving_input_receiver. This function builds a part of a tf.Graph that parses the raw data received by the SavedModel.

The tf.estimator.export module contains functions to help build these receivers.

The following code builds a receiver, based on the feature_columns, that accepts serialized tf.Example protocol buffers, which are often used with tf-serving.

tmpdir = tempfile.mkdtemp()

serving_input_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn(
  tf.feature_column.make_parse_example_spec([input_column]))

estimator_base_path = os.path.join(tmpdir, 'from_estimator')
estimator_path = estimator.export_saved_model(estimator_base_path, serving_input_fn)

You can also load and run that model, from python:

imported = tf.saved_model.load(estimator_path)

def predict(x):
  example = tf.train.Example()
  example.features.feature["x"].float_list.value.extend([x])
  return imported.signatures["predict"](
    examples=tf.constant([example.SerializeToString()]))

print(predict(1.5))
print(predict(3.5))

Click here!