使用超参数调节

trainingInput:
  scaleTier: CUSTOM
  masterType: complex_model_m
  workerType: complex_model_m
  parameterServerType: large_model
  workerCount: 9
  parameterServerCount: 3
  hyperparameters:
    goal: MAXIMIZE
    hyperparameterMetricTag: metric1
    maxTrials: 30
    maxParallelTrials: 1
    enableTrialEarlyStopping: True
    params:
    - parameterName: hidden1
      type: INTEGER
      minValue: 40
      maxValue: 400
      scaleType: UNIT_LINEAR_SCALE
    - parameterName: numRnnCells
      type: DISCRETE
      discreteValues:
      - 1
      - 2
      - 3
      - 4
    - parameterName: rnnCellType
      type: CATEGORICAL
      categoricalValues:
      - BasicLSTMCell
      - BasicRNNCell
      - GRUCell
      - LSTMCell
      - LayerNormBasicLSTMCell

# Add hyperparameter tuning to the job config.
hyperparams = {
    'goal': 'MAXIMIZE',
    'hyperparameterMetricTag': 'metric1',
    'maxTrials': 30,
    'maxParallelTrials': 1,
    'enableTrialEarlyStopping': True,
    'params': []}

hyperparams['params'].append({
    'parameterName':'hidden1',
    'type':'INTEGER',
    'minValue': 40,
    'maxValue': 400,
    'scaleType': 'UNIT_LINEAR_SCALE'})

hyperparams['params'].append({
    'parameterName':'numRnnCells',
    'type':'DISCRETE',
    'discreteValues': [1, 2, 3, 4]})

hyperparams['params'].append({
    'parameterName':'rnnCellType',
    'type': 'CATEGORICAL',
    'categoricalValues': [
        'BasicLSTMCell',
        'BasicRNNCell',
        'GRUCell',
        'LSTMCell',
        'LayerNormBasicLSTMCell'
    ]
})

# Add hyperparameter specification to the training inputs dictionary.
training_inputs['hyperparameters'] = hyperparams

# Build the job spec.
job_spec = {'jobId': my_job_name, 'trainingInput': training_inputs}

class MyMetricCallback(tf.keras.callbacks.Callback):

    def on_epoch_end(self, epoch, logs=None):
        tf.summary.scalar('metric1', logs['RootMeanSquaredError'], epoch)

logdir = "logs/scalars/" + datetime.now().strftime("%Y%m%d-%H%M%S")
file_writer = tf.summary.create_file_writer(logdir + "/metrics")
file_writer.set_as_default()

model = tf.keras.Sequential(
    tf.keras.layers.Dense(1, activation='linear', input_dim=784))
model.compile(
    optimizer='rmsprop',
    loss='mean_squared_error',
    metrics=['RootMeanSquaredError'])

model.fit(
    x_train,
    y_train,
    batch_size=64,
    epochs=10,
    steps_per_epoch=5,
    verbose=0,
    callbacks=[MyMetricCallback()])

# Create metric for hyperparameter tuning
def my_metric(labels, predictions):
    # Note that different types of estimator provide different different
    # keys on the predictions Tensor. predictions['predictions'] is for
    # regression output.
    pred_values = predictions['predictions']
    return {'metric1': tf.compat.v1.metrics.root_mean_squared_error(labels, pred_values)}

# Create estimator to train and evaluate
def train_and_evaluate(output_dir):

    estimator = tf.estimator.DNNLinearCombinedRegressor(...)

    estimator = tf.estimator.add_metrics(estimator, my_metric)

    train_spec = ...
    eval_spec = tf.estimator.EvalSpec(
        start_delay_secs = 60, # start evaluating after 60 seconds
        throttle_secs = 300,  # evaluate every 300 seconds
        ...)
    tf.estimator.train_and_evaluate(estimator, train_spec, eval_spec)

trainingInput:
  scaleTier: CUSTOM
  masterType: complex_model_m
  workerType: complex_model_m
  parameterServerType: large_model
  workerCount: 9
  parameterServerCount: 3
  hyperparameters:
    enableTrialEarlyStopping: TRUE
    maxTrials: 30
    maxParallelTrials: 1
    resumePreviousJobId: [PREVIOUS_JOB_IDENTIFIER]

# Add hyperparameter tuning to the job config.
hyperparams = {
    'enableTrialEarlyStopping': True,
    'maxTrials': 30,
    'maxParallelTrials': 1,
    'resumePreviousJobId': [PREVIOUS_JOB_IDENTIFIER]}

# Add the hyperparameter specification to the training inputs dictionary.
training_inputs['hyperparameters'] = hyperparams

# Build the job spec.
job_spec = {'jobId': my_job_name, 'trainingInput': training_inputs}