Documentation

Module

Reduction

Methods

# inner maxValue(tensor, axis) → {Tensor}

Computes the maximum of elements across dimensions of a tf.Tensor.
Parameters:
Name Type Description
tensor Tensor The input tensor.
axis Number | Array.<Number> The dimension(s) to reduce. By default it reduces all dimensions.

View Source

tf.max(tensor, axis)
Tensor

# inner maxValueIndex(tensor, axis) → {Tensor}

Returns the indices of the maximum values along an axis.
Parameters:
Name Type Description
tensor Tensor The input tensor.
axis Number | Array.<Number> The dimension to reduce. Defaults to 0 (outer-most dimension).

View Source

tf.argMax(tensor, axis)
Tensor

# inner reduceMean(tensor, axis, keepDims) → {Tensor}

Computes the mean of elements across dimensions of a tf.Tensor.
Parameters:
Name Type Description
tensor Tensor The input tensor.
axis Number | Array.<Number> The dimension(s) to reduce. By default it reduces all dimensions.
keepDims Boolean If true, retains reduced dimensions with size 1.

View Source

tf.mean(tensor, axis, keepDims)
Tensor

# inner reduceProd(tensor, axis) → {Tensor}

Computes the product of elements across dimensions of a tf.Tensor.
Parameters:
Name Type Description
tensor Tensor The input tensor to compute the product over. If the dtype is bool it will be converted to int32 and the output dtype will be int32.
axis Number | Array.<Number> The dimension(s) to reduce. By default it reduces all dimensions.

View Source

tf.prod(tensor, axis)
Tensor

# inner reduceSum(tensor, axis, keepDims) → {Tensor}

Computes the sum of elements across dimensions of a tf.Tensor.
Parameters:
Name Type Description
tensor Tensor The input tensor to compute the sum over. If the dtype is bool it will be converted to int32 and the output dtype will be int32.
axis Number | Array.<Number> The dimension(s) to reduce. By default it reduces all dimensions.
keepDims Boolean If true, retains reduced dimensions with size 1.

View Source

tf.sum(tensor, axis, keepDims)
Tensor