Add support for TensorFlow 1.11.0 and bump library version up to 1.12.0 (#439)

* Add support for tensorflow 1.11.0 and bump library version up to 1.12.0

Author: mvsusp

CHANGELOG.rst

@@ -2,6 +2,11 @@
 CHANGELOG
 =========
 
+1.12.0
+======
+
+* feature: add support for TensorFlow 1.11.0
+
 1.11.3
 ======
 

README.rst

@@ -283,7 +283,7 @@ TensorFlow SageMaker Estimators
 
 By using TensorFlow SageMaker ``Estimators``, you can train and host TensorFlow models on Amazon SageMaker.
 
-Supported versions of TensorFlow: ``1.4.1``, ``1.5.0``, ``1.6.0``, ``1.7.0``, ``1.8.0``, ``1.9.0``, ``1.10.0``.
+Supported versions of TensorFlow: ``1.4.1``, ``1.5.0``, ``1.6.0``, ``1.7.0``, ``1.8.0``, ``1.9.0``, ``1.10.0``, ``1.11.0``.
 
 We recommend that you use the latest supported version, because that's where we focus most of our development efforts.
 

src/sagemaker/__init__.py

@@ -35,4 +35,4 @@
 from sagemaker.session import s3_input  # noqa: F401
 from sagemaker.session import get_execution_role  # noqa: F401
 
-__version__ = '1.11.3'
+__version__ = '1.12.0'

src/sagemaker/fw_utils.py

@@ -159,7 +159,7 @@ def framework_name_from_image(image_name):
             str: The image tag
     """
     # image name format: <account>.dkr.ecr.<region>.amazonaws.com/sagemaker-<framework>-<py_ver>-<device>:<tag>
-    sagemaker_pattern = re.compile('^(\d+)(\.)dkr(\.)ecr(\.)(.+)(\.)amazonaws.com(/)(.*:.*)$')
+    sagemaker_pattern = re.compile(r'^(\d+)(\.)dkr(\.)ecr(\.)(.+)(\.)amazonaws.com(/)(.*:.*)$')
     sagemaker_match = sagemaker_pattern.match(image_name)
     if sagemaker_match is None:
         return None, None, None

src/sagemaker/session.py

@@ -1050,8 +1050,8 @@ def _deployment_entity_exists(describe_fn):
         describe_fn()
         return True
     except ClientError as ce:
-        if not (ce.response['Error']['Code'] == 'ValidationException' and
-                'Could not find' in ce.response['Error']['Message']):
+        error_code = ce.response['Error']['Code']
+        if not (error_code == 'ValidationException' and 'Could not find' in ce.response['Error']['Message']):
             raise ce
         return False
 

src/sagemaker/tensorflow/README.rst

@@ -6,7 +6,7 @@ TensorFlow SageMaker Estimators allow you to run your own TensorFlow
 training algorithms on SageMaker Learner, and to host your own TensorFlow
 models on SageMaker Hosting.
 
-Supported versions of TensorFlow: ``1.4.1``, ``1.5.0``, ``1.6.0``, ``1.7.0``, ``1.8.0``, ``1.9.0``, ``1.10.0``.
+Supported versions of TensorFlow: ``1.4.1``, ``1.5.0``, ``1.6.0``, ``1.7.0``, ``1.8.0``, ``1.9.0``, ``1.10.0``, ``1.11.0``.
 
 Training with TensorFlow
 ~~~~~~~~~~~~~~~~~~~~~~~~

src/sagemaker/tensorflow/defaults.py

@@ -12,4 +12,4 @@
 # language governing permissions and limitations under the License.
 from __future__ import absolute_import
 
-TF_VERSION = '1.10'
+TF_VERSION = '1.11'

tests/conftest.py

@@ -81,7 +81,7 @@ def sagemaker_local_session(boto_config):
 
 @pytest.fixture(scope='module', params=['1.4', '1.4.1', '1.5', '1.5.0', '1.6', '1.6.0',
                                         '1.7', '1.7.0', '1.8', '1.8.0', '1.9', '1.9.0',
-                                        '1.10', '1.10.0'])
+                                        '1.10', '1.10.0', '1.11', '1.11.0'])
 def tf_version(request):
     return request.param
 

tests/data/cifar_10/source/keras_cnn_cifar_10.py

@@ -10,17 +10,12 @@
 # distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
 # ANY KIND, either express or implied. See the License for the specific
 # language governing permissions and limitations under the License.
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import os
+from __future__ import absolute_import, division, print_function
 
 import tensorflow as tf
-from tensorflow.python.keras.layers import InputLayer, Conv2D, Activation, MaxPooling2D, Dropout, Flatten, Dense
+from tensorflow.python.keras.layers import Activation, Conv2D, Dense, Dropout, Flatten, MaxPooling2D
 from tensorflow.python.keras.models import Sequential
-from tensorflow.python.keras.optimizers import RMSprop
-from tensorflow.python.saved_model.signature_constants import PREDICT_INPUTS
+from tensorflow.python.training.rmsprop import RMSPropOptimizer
 
 HEIGHT = 32
 WIDTH = 32
@@ -29,7 +24,7 @@
 NUM_DATA_BATCHES = 5
 NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 10000 * NUM_DATA_BATCHES
 BATCH_SIZE = 128
-INPUT_TENSOR_NAME = PREDICT_INPUTS
+INPUT_TENSOR_NAME = 'inputs_input'  # needs to match the name of the first layer + "_input"
 
 
 def keras_model_fn(hyperparameters):
@@ -43,10 +38,7 @@ def keras_model_fn(hyperparameters):
     """
     model = Sequential()
 
-    # TensorFlow Serving default prediction input tensor name is PREDICT_INPUTS.
-    # We must conform to this naming scheme.
-    model.add(InputLayer(input_shape=(HEIGHT, WIDTH, DEPTH), name=PREDICT_INPUTS))
-    model.add(Conv2D(32, (3, 3), padding='same'))
+    model.add(Conv2D(32, (3, 3), padding='same', name='inputs', input_shape=(HEIGHT, WIDTH, DEPTH)))
     model.add(Activation('relu'))
     model.add(Conv2D(32, (3, 3)))
     model.add(Activation('relu'))
@@ -67,19 +59,17 @@ def keras_model_fn(hyperparameters):
     model.add(Dense(NUM_CLASSES))
     model.add(Activation('softmax'))
 
-    _model = tf.keras.Model(inputs=model.input, outputs=model.output)
-
-    opt = RMSprop(lr=hyperparameters['learning_rate'], decay=hyperparameters['decay'])
+    opt = RMSPropOptimizer(learning_rate=hyperparameters['learning_rate'], decay=hyperparameters['decay'])
 
-    _model.compile(loss='categorical_crossentropy',
-                   optimizer=opt,
-                   metrics=['accuracy'])
+    model.compile(loss='categorical_crossentropy',
+                  optimizer=opt,
+                  metrics=['accuracy'])
 
-    return _model
+    return model
 
 
 def serving_input_fn(hyperpameters):
-    inputs = {PREDICT_INPUTS: tf.placeholder(tf.float32, [None, 32, 32, 3])}
+    inputs = {INPUT_TENSOR_NAME: tf.placeholder(tf.float32, [None, 32, 32, 3])}
     return tf.estimator.export.ServingInputReceiver(inputs, inputs)
 
 

tests/integ/test_tf_keras.py

@@ -33,7 +33,7 @@ def test_keras(sagemaker_session, tf_full_version):
                                source_dir=script_path,
                                role='SageMakerRole', sagemaker_session=sagemaker_session,
                                hyperparameters={'learning_rate': 1e-4, 'decay': 1e-6},
-                               training_steps=500, evaluation_steps=5,
+                               training_steps=50, evaluation_steps=5,
                                train_instance_count=1, train_instance_type='ml.c4.xlarge',
                                train_max_run=45 * 60)
 

tests/integ/test_tuner.py

@@ -286,7 +286,7 @@ def test_tuning_chainer(sagemaker_session):
 
         objective_metric_name = 'Validation-accuracy'
         metric_definitions = [
-            {'Name': 'Validation-accuracy', 'Regex': '\[J1\s+\d\.\d+\s+\d\.\d+\s+\d\.\d+\s+(\d\.\d+)'}]
+            {'Name': 'Validation-accuracy', 'Regex': r'\[J1\s+\d\.\d+\s+\d\.\d+\s+\d\.\d+\s+(\d\.\d+)'}]
 
         tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges, metric_definitions,
                                     max_jobs=2, max_parallel_jobs=2)
@@ -327,7 +327,7 @@ def test_attach_tuning_pytorch(sagemaker_session):
 
     with timeout(minutes=TUNING_DEFAULT_TIMEOUT_MINUTES):
         objective_metric_name = 'evaluation-accuracy'
-        metric_definitions = [{'Name': 'evaluation-accuracy', 'Regex': 'Overall test accuracy: (\d+)'}]
+        metric_definitions = [{'Name': 'evaluation-accuracy', 'Regex': r'Overall test accuracy: (\d+)'}]
         hyperparameter_ranges = {'batch-size': IntegerParameter(50, 100)}
 
         tuner = HyperparameterTuner(estimator, objective_metric_name, hyperparameter_ranges, metric_definitions,

tests/integ/timeout.py

@@ -96,8 +96,8 @@ def _show_endpoint_logs(endpoint_name, sagemaker_session):
                        aws_region=sagemaker_session.boto_session.region_name)
         logs.list_logs()
     except Exception:
-        LOGGER.exception('Failure occurred while listing cloudwatch log group %s. ' +
-                         'Swallowing exception but printing stacktrace for debugging.', log_group)
+        LOGGER.exception('Failure occurred while listing cloudwatch log group %s. Swallowing exception but printing '
+                         'stacktrace for debugging.', log_group)
 
 
 def _cleanup_endpoint_logs(endpoint_name, sagemaker_session):
@@ -109,5 +109,5 @@ def _cleanup_endpoint_logs(endpoint_name, sagemaker_session):
         cwl_client.delete_log_group(logGroupName=log_group)
         LOGGER.info('deleted cloudwatch log group: {}'.format(log_group))
     except Exception:
-        LOGGER.exception('Failure occurred while cleaning up cloudwatch log group %s. ' +
+        LOGGER.exception('Failure occurred while cleaning up cloudwatch log group %s. '
                          'Swallowing exception but printing stacktrace for debugging.', log_group)