Module dfdx::tensor_ops
source · [−]Expand description
Implementations of all operations for tensors, including activations, binary operations, and other methods.
Traits
Functions
Applies a DifferentiableFunction to the tensor.
Clamps all values in t
to between min
and max
Numerically stable computation of log(softmax(t))
. Does t - logsumexp(t)
under the hood.
Computes the LogSumExp function.
Equivalent to Log(sum(exp(data)))
or data.exp().sum(-1).log()
.
Matrix multiplication.
Replaces any nans in t
with value
.
Negates all values in t
.
Computes the softmax function.
Equivalent to t.log_softmax().exp()
or exp(log_softmax(t))
or exp(t) / sum(exp(t))
Sets t
to value
anywhere mask
equals value
vector * matrix multiplication.