Python tensorflow.python.training.moving_averages.ExponentialMovingAverage() Examples

The following are 5 code examples of tensorflow.python.training.moving_averages.ExponentialMovingAverage(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.python.training.moving_averages , or try the search function .
Example #1
Source File: moving_average_optimizer.py    From lambda-packs with MIT License 6 votes vote down vote up 
def __init__(self, opt, average_decay=0.9999, num_updates=None,
               sequential_update=True):
    """Construct a new MovingAverageOptimizer.

    Args:
      opt: A tf.Optimizer that will be used to compute and apply gradients.
      average_decay: Float.  Decay to use to maintain the moving averages
                     of trained variables.
                     See tf.train.ExponentialMovingAverage for details.
      num_updates: Optional count of number of updates applied to variables.
                   See tf.train.ExponentialMovingAverage for details.
      sequential_update: Bool. If False, will compute the moving average at the
                         same time as the model is updated, potentially doing
                         benign data races.
                         If True, will update the moving average after gradient
                         updates.
    """
    self._optimizer = opt
    self._ema = moving_averages.ExponentialMovingAverage(
        average_decay, num_updates=num_updates)
    self._variable_map = None
    self._sequential_update = sequential_update
Example #2
Source File: moving_average_optimizer.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def __init__(self, opt, average_decay=0.9999, num_updates=None,
               sequential_update=True):
    """Construct a new MovingAverageOptimizer.

    Args:
      opt: A tf.Optimizer that will be used to compute and apply gradients.
      average_decay: Float.  Decay to use to maintain the moving averages
                     of trained variables.
                     See tf.train.ExponentialMovingAverage for details.
      num_updates: Optional count of number of updates applied to variables.
                   See tf.train.ExponentialMovingAverage for details.
      sequential_update: Bool. If False, will compute the moving average at the
                         same time as the model is updated, potentially doing
                         benign data races.
                         If True, will update the moving average after gradient
                         updates.
    """
    self._optimizer = opt
    self._ema = moving_averages.ExponentialMovingAverage(
        average_decay, num_updates=num_updates)
    self._variable_map = None
    self._sequential_update = sequential_update
Example #3
Source File: moving_average_optimizer.py    From deep_image_model with Apache License 2.0 6 votes vote down vote up 
def __init__(self, opt, average_decay=0.9999, num_updates=None,
               sequential_update=True):
    """Construct a new MovingAverageOptimizer.

    Args:
      opt: A tf.Optimizer that will be used to compute and apply gradients.
      average_decay: Float.  Decay to use to maintain the moving averages
                     of trained variables.
                     See tf.train.ExponentialMovingAverage for details.
      num_updates: Optional count of number of updates applied to variables.
                   See tf.train.ExponentialMovingAverage for details.
      sequential_update: Bool. If False, will compute the moving average at the
                         same time as the model is updated, potentially doing
                         benign data races.
                         If True, will update the moving average after gradient
                         updates.
    """
    self._optimizer = opt
    self._ema = moving_averages.ExponentialMovingAverage(
        average_decay, num_updates=num_updates)
    self._variable_map = None
    self._sequential_update = sequential_update
Example #4
Source File: moving_average_optimizer.py    From keras-lambda with MIT License 6 votes vote down vote up 
def __init__(self, opt, average_decay=0.9999, num_updates=None,
               sequential_update=True):
    """Construct a new MovingAverageOptimizer.

    Args:
      opt: A tf.Optimizer that will be used to compute and apply gradients.
      average_decay: Float.  Decay to use to maintain the moving averages
                     of trained variables.
                     See tf.train.ExponentialMovingAverage for details.
      num_updates: Optional count of number of updates applied to variables.
                   See tf.train.ExponentialMovingAverage for details.
      sequential_update: Bool. If False, will compute the moving average at the
                         same time as the model is updated, potentially doing
                         benign data races.
                         If True, will update the moving average after gradient
                         updates.
    """
    self._optimizer = opt
    self._ema = moving_averages.ExponentialMovingAverage(
        average_decay, num_updates=num_updates)
    self._variable_map = None
    self._sequential_update = sequential_update
Example #5
Source File: sparse_optimizers.py    From rigl with Apache License 2.0 5 votes vote down vote up 
def __init__(self, optimizer, begin_step, end_step, frequency,
               drop_fraction=0.1, drop_fraction_anneal='constant',
               use_locking=False, grow_init='zeros', momentum=0.9,
               use_tpu=False, name='SparseMomentumOptimizer',
               stateless_seed_offset=0):
    super(SparseMomentumOptimizer, self).__init__(
        optimizer, begin_step, end_step, frequency, drop_fraction=drop_fraction,
        drop_fraction_anneal=drop_fraction_anneal, grow_init=grow_init,
        use_locking=use_locking, name='SparseMomentumOptimizer',
        stateless_seed_offset=stateless_seed_offset)
    self._ema_grads = moving_averages.ExponentialMovingAverage(decay=momentum)
    self._use_tpu = use_tpu