vm.tensorflow

Classes

class GradientTape : Record the operations for auto differentiation.

class TensorShape : Represent the a sequence of dimensions.

class TensorSpec : Spec to describe properties of a tensor.

Functions

broadcast_to(…) : Broadcast input according to a given shape.

cast(…) : Cast the data type of input.

clip_by_value(…) : Compute the clipped input according to the given bounds.

concat(…) : Concatenate the values along the given axis.

constant(…) : Return a tensor initialized from the value.

device(…) : Context-manager to nest the the device spec.

expand_dims(…) : Expand the dimensions of input with size 1.

eye(…) : Return a tensor constructed as the identity matrix.

fill(…) : Return a tensor filled with the scalar value.

gather(…) : Select the elements according to the index along the given axis.

function(…) : Create a callable graph from the python function.

gradients(…) : Compute the symbolic derivatives of ys w.r.t. xs .

identity(…) : Return a new tensor copying the content of input.

name_scope(…) : Context-manager to nest the name as prefix for operations.

ones(…) : Return a tensor filled with ones.

ones_like(…) : Return a tensor of ones with shape as the other.

one_hot(…) : Return the one-hot representation for input.

pad(…) : Pad the input according to the given sizes.

range(…) : Return a tensor of evenly spaced values within a interval.

reshape(…) : Change the dimensions of input.

shape(…) : Return the shape of input.

slice(…) : Select the elements according to the given sections.

split(…) : Split input into chunks along the given axis.

squeeze(…) : Remove the dimensions of input with size 1.

transpose(…) : Permute the dimensions of input.

unique(…) : Return the unique elements of input.

unique_with_counts(…) : Return the unique elements of input with counts.

zeros(…) : Return a tensor filled with zeros.

zeros_like(…) : Return a tensor of zeros with shape as the other.