tensorflow_model_optimization/python/core/common/keras/compression/algorithms/different_training_and_inference.py [44:62]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    rank = self.rank
    s, u, v = tf.linalg.svd(weight)

    if len(weight.shape) == 2:
      # FC Layer
      s = s[:rank]
      u = u[:, :rank]
      v = v[:, :rank]
    elif len(weight.shape) == 4:
      # Conv2D Layer
      s = s[:, :, :rank]
      u = u[:, :, :, :rank]
      v = v[:, :, :, :rank]
    else:
      raise NotImplementedError('Only for dimension=2 or 4 is supported.')

    sv = tf.matmul(tf.linalg.diag(s), v, adjoint_b=True)

    return [u, sv]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_model_optimization/python/core/common/keras/compression/algorithms/periodical_update_and_scheduling.py [91:109]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    rank = self.rank
    s, u, v = tf.linalg.svd(weight)

    if len(weight.shape) == 2:
      # FC Layer
      s = s[:rank]
      u = u[:, :rank]
      v = v[:, :rank]
    elif len(weight.shape) == 4:
      # Conv2D Layer
      s = s[:, :, :rank]
      u = u[:, :, :, :rank]
      v = v[:, :, :, :rank]
    else:
      raise NotImplementedError('Only for dimension=2 or 4 is supported.')

    sv = tf.matmul(tf.linalg.diag(s), v, adjoint_b=True)

    return [u, sv]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -