Tensorflow モデル分析アーキテクチャ

# Extracts represent data extracted during pipeline processing.
# For example, the PredictExtractor stores the data for the
# features, labels, and predictions under the keys "features",
# "labels", and "predictions".
Extracts = Dict[Text, Any]

# Evaluation represents the output from evaluating extracts at
# particular point in the pipeline. The evaluation outputs are
# keyed by their associated output type. For example, the metric / plot
# dictionaries from evaluating metrics and plots will be stored under
# "metrics" and "plots" respectively.
Evaluation = Dict[Text, beam.pvalue.PCollection]

# An Extractor is a PTransform that takes Extracts as input and returns
# Extracts as output. A typical example is a PredictExtractor that receives
# an 'input' placeholder for input and adds additional 'predictions' extracts.
Extractor = NamedTuple('Extractor', [
    ('stage_name', Text),
    ('ptransform', beam.PTransform)])  # Extracts -> Extracts

# An evaluator is a PTransform that takes Extracts as input and
# produces an Evaluation as output. A typical example of an evaluator
# is the MetricsAndPlotsEvaluator that takes the 'features', 'labels',
# and 'predictions' extracts from the PredictExtractor and evaluates
# them using post export metrics to produce metrics and plots dictionaries.
Evaluator = NamedTuple('Evaluator', [
  ('stage_name', Text),
  ('run_after', Text),              # Extractor.stage_name
  ('ptransform', beam.PTransform)]) # Extracts -> Evaluation

# A writer is a PTransform that takes evaluation output as input and
# serializes the associated PCollections of data to a sink.
Writer = NamedTuple('Writer', [
  ('stage_name', Text),
  ('ptransform', beam.PTransform)])    # Evaluation -> PDone

tfma.writers.Writer(
  stage_name='WriteTFRecord(%s)' % tfma.METRICS_KEY,
  ptransform=tfma.writers.Write(
    key=tfma.METRICS_KEY,
    ptransform=beam.io.WriteToTFRecord(file_path_prefix=output_file))

run_model_analysis(
    ...
    extractors=[
        tfma.extractors.InputExtractor(...),
        tfma.extractors.PredictExtractor(...),
        tfma.extractors.SliceKeyExtrator(...)
    ],
    evaluators=[
        tfma.evaluators.MetricsAndPlotsEvaluator(...),
        tfma.evaluators.AnalysisTableEvaluator(...)
    ])

# Out
Extracts {
  'input': bytes                 # CSV, Proto, ...
}

# In:  ReadInputs Extracts
# Out:
Extracts {
  'input': bytes                    # CSV, Proto, ...
  'features': tensor_like           # Raw features
  'labels': tensor_like             # Labels
  'example_weights': tensor_like    # Example weights
}

# In:  InputExtractor Extracts
# Out:
Extracts {
  'input': bytes                    # CSV, Proto, ...
  'features': tensor_like           # Raw features
  'labels': tensor_like             # Labels
  'example_weights': tensor_like    # Example weights
  'predictions': tensor_like        # Predictions
}

# In: PredictExtractor Extracts
# Out:
Extracts {
  'features': tensor_like           # Raw features
  'labels': tensor_like             # Labels
  'example_weights': tensor_like    # Example weights
  'predictions': tensor_like        # Predictions
  'slice_key': Tuple[bytes...]      # Slice
}

# In: SliceKeyExtractor Extracts
# Out:
Evaluation {
  'metrics': PCollection[Tuple[slicer.SliceKeyType, Dict[Text, Any]]]  # Tuples of (slice key, dictionary from metric key to metric values)
  'plots': PCollection[Tuple[slicer.SliceKeyType, Dict[Text, Any]]]  # Tuples of (slice key, dictionary from plot key to plot values)
}

# In: SliceKeyExtractor Extracts
# Out:
Evaluation {
  'analysis': PCollection[Extracts] # Final Extracts
}

# In:
Evaluation {
  'metrics': PCollection[Tuple[slicer.SliceKeyType, Dict[Text, Any]]]  # Tuples of (slice key, dictionary from metric key to metric values)
  'plots': PCollection[Tuple[slicer.SliceKeyType, Dict[Text, Any]]]  # Tuples of (slice key, dictionary from plot key to plot values)
  'analysis': PCollection[Extracts] # Final Extracts
}
# Out: metrics, plots, and analysis files