Enum TensorLossError 

pub enum TensorLossError {
    ShapeMismatch {
        expected: Vec<usize>,
        got: Vec<usize>,
    },
    InvalidTarget(String),
    DivisionByZero,
    EmptyInput,
    InvalidConfig(String),
}

Errors that can occur during tensor-level loss computation.

Variants

ShapeMismatch

The prediction and target tensors have different shapes.

Fields

expected: Vec<usize>

got: Vec<usize>

InvalidTarget(String)

The target tensor contains an invalid value (e.g. out of [0,1] for BCE).

DivisionByZero

A division-by-zero was encountered (e.g. zero-norm vector in cosine loss).

EmptyInput

The input tensor has no elements.

InvalidConfig(String)

The loss was configured with an invalid parameter value.

Trait Implementations

impl Clone for TensorLossError

fn clone(&self) -> TensorLossError

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TensorLossError

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for TensorLossError

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Error for TensorLossError

fn source(&self) -> Option<&(dyn Error + 'static)>

Returns the lower-level source of this error, if any.

fn description(&self) -> &str

👎Deprecated since 1.42.0:

use the Display impl or to_string()

fn cause(&self) -> Option<&dyn Error>

👎Deprecated since 1.33.0:

replaced by Error::source, which can support downcasting

fn provide<'a>(&'a self, request: &mut Request<'a>)

🔬This is a nightly-only experimental API. (error_generic_member_access)

Provides type-based access to context intended for error reports.