Help protect the Great Barrier Reef with TensorFlow on Kaggle Join Challenge

SparseApplyAdagradV2

public final class SparseApplyAdagradV2

Update relevant entries in '*var' and '*accum' according to the adagrad scheme.

That is for rows we have grad for, we update var and accum as follows:

$$accum += grad * grad$$
$$var -= lr * grad * (1 / sqrt(accum))$$

Nested Classes

class SparseApplyAdagradV2.Options Optional attributes for SparseApplyAdagradV2  

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of a tensor.
static <T, U extends Number> SparseApplyAdagradV2<T>
create(Scope scope, Operand<T> var, Operand<T> accum, Operand<T> lr, Operand<T> epsilon, Operand<T> grad, Operand<U> indices, Options... options)
Factory method to create a class wrapping a new SparseApplyAdagradV2 operation.
Output<T>
out()
Same as "var".
static SparseApplyAdagradV2.Options
updateSlots(Boolean updateSlots)
static SparseApplyAdagradV2.Options
useLocking(Boolean useLocking)

Inherited Methods

Public Methods

public Output<T> asOutput ()

Returns the symbolic handle of a tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static SparseApplyAdagradV2<T> create (Scope scope, Operand<T> var, Operand<T> accum, Operand<T> lr, Operand<T> epsilon, Operand<T> grad, Operand<U> indices, Options... options)

Factory method to create a class wrapping a new SparseApplyAdagradV2 operation.

Parameters
scope current scope
var Should be from a Variable().
accum Should be from a Variable().
lr Learning rate. Must be a scalar.
epsilon Constant factor. Must be a scalar.
grad The gradient.
indices A vector of indices into the first dimension of var and accum.
options carries optional attributes values
Returns
  • a new instance of SparseApplyAdagradV2

public Output<T> out ()

Same as "var".

public static SparseApplyAdagradV2.Options updateSlots (Boolean updateSlots)

public static SparseApplyAdagradV2.Options useLocking (Boolean useLocking)

Parameters
useLocking If `True`, updating of the var and accum tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.