在为 TFX 设计 TensorFlow 模型代码时，需要注意一些事项，包括选择模型 API。
- 消耗：来自 Transform 的 SavedModel，以及来自 ExampleGen 的数据
- 发出：以 SavedModel 格式训练的模型
模型的输入层应从由 Transform 组件创建的 SavedModel 中获取数据，并且 Transform 模型的层应包含在模型中，以便在导出 SavedModel 和 EvalSavedModel 时，它们将包含由 Transform 组件创建的转换。
用于 TFX 的典型 TensorFlow 模型设计如下所示
def _build_estimator(tf_transform_dir,
config,
hidden_units=None,
warm_start_from=None):
"""Build an estimator for predicting the tipping behavior of taxi riders.
Args:
tf_transform_dir: directory in which the tf-transform model was written
during the preprocessing step.
config: tf.contrib.learn.RunConfig defining the runtime environment for the
estimator (including model_dir).
hidden_units: [int], the layer sizes of the DNN (input layer first)
warm_start_from: Optional directory to warm start from.
Returns:
Resulting DNNLinearCombinedClassifier.
"""
metadata_dir = os.path.join(tf_transform_dir,
transform_fn_io.TRANSFORMED_METADATA_DIR)
transformed_metadata = metadata_io.read_metadata(metadata_dir)
transformed_feature_spec = transformed_metadata.schema.as_feature_spec()
transformed_feature_spec.pop(_transformed_name(_LABEL_KEY))
real_valued_columns = [
tf.feature_column.numeric_column(key, shape=())
for key in _transformed_names(_DENSE_FLOAT_FEATURE_KEYS)
]
categorical_columns = [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=_VOCAB_SIZE + _OOV_SIZE, default_value=0)
for key in _transformed_names(_VOCAB_FEATURE_KEYS)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=_FEATURE_BUCKET_COUNT, default_value=0)
for key in _transformed_names(_BUCKET_FEATURE_KEYS)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=num_buckets, default_value=0)
for key, num_buckets in zip(
_transformed_names(_CATEGORICAL_FEATURE_KEYS), #
_MAX_CATEGORICAL_FEATURE_VALUES)
]
return tf.estimator.DNNLinearCombinedClassifier(
config=config,
linear_feature_columns=categorical_columns,
dnn_feature_columns=real_valued_columns,
dnn_hidden_units=hidden_units or [100, 70, 50, 25],
warm_start_from=warm_start_from)