# tf.contrib.kfac.fisher_blocks.FullFB

## Class FullFB

Inherits From: FisherBlock

FisherBlock using a full matrix estimate (no approximations).

FullFB uses a full matrix estimate (no approximations), and should only ever be used for very low dimensional parameters.

Note that this uses the naive "square the sum estimator", and so is applicable to any type of parameter in principle, but has very high variance.

## Methods

### __init__

__init__(
layer_collection,
params
)


Creates a FullFB block.

#### Args:

• layer_collection: The collection of all layers in the K-FAC approximate Fisher information matrix to which this FisherBlock belongs.
• params: The parameters of this layer (Tensor or tuple of Tensors).

### full_fisher_block

full_fisher_block()


Explicitly constructs the full Fisher block.

### instantiate_factors

instantiate_factors(
damping
)


### multiply

multiply(vector)


Multiplies the vector by the (damped) block.

#### Args:

• vector: The vector (a Tensor or tuple of Tensors) to be multiplied.

#### Returns:

The vector left-multiplied by the (damped) block.

### multiply_inverse

multiply_inverse(vector)


Multiplies the vector by the (damped) inverse of the block.

#### Args:

• vector: The vector (a Tensor or tuple of Tensors) to be multiplied.

#### Returns:

The vector left-multiplied by the (damped) inverse of the block.

### multiply_matpower

multiply_matpower(
vector,
exp
)


### register_additional_tower

register_additional_tower(batch_size)


#### Args:

• batch_size: The batch size, used in the covariance estimator.

### register_inverse

register_inverse()


Registers a matrix inverse to be computed by the block.

### register_matpower

register_matpower(exp)


### tensors_to_compute_grads

tensors_to_compute_grads()