Enum InferenceError 

#[non_exhaustive]
pub enum InferenceError {
    ModelLoadFailed {
        path: String,
        reason: String,
    },
    InputShapeMismatch {
        expected: Vec<usize>,
        actual: Vec<usize>,
    },
    OutputShapeMismatch {
        expected: Vec<usize>,
        actual: Vec<usize>,
    },
    GpuError {
        message: String,
    },
    InferenceFailed {
        message: String,
    },
    ModelNotInitialized {
        name: String,
    },
    UnsupportedFormat {
        format: String,
    },
    QuantizationError {
        message: String,
    },
    InvalidBatchSize {
        size: usize,
        max_size: usize,
    },
}

Errors related to neural network inference.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

ModelLoadFailed

Model file not found or could not be loaded

Fields

path: String

Path to the model file

reason: String

Reason for the failure

InputShapeMismatch

Input tensor shape mismatch

Fields

expected: Vec<usize>

Expected tensor shape

actual: Vec<usize>

Actual tensor shape

OutputShapeMismatch

Output tensor shape mismatch

Fields

expected: Vec<usize>

Expected tensor shape

actual: Vec<usize>

Actual tensor shape

GpuError

CUDA/GPU error

Fields

message: String

Description of the GPU error

InferenceFailed

Model inference failed

Fields

message: String

Description of the failure

ModelNotInitialized

Model not initialized

Fields

name: String

Name of the uninitialized model

UnsupportedFormat

Unsupported model format

Fields

format: String

The unsupported format

QuantizationError

Quantization error

Fields

message: String

Description of the quantization error

InvalidBatchSize

Batch size error

Fields

size: usize

The invalid batch size

max_size: usize

Maximum allowed batch size

Implementations

impl InferenceError

pub const fn is_recoverable(&self) -> bool

Returns true if this error is recoverable.

Trait Implementations

impl Debug for InferenceError

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

Formats the value using the given formatter.

impl Display for InferenceError

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

Formats the value using the given formatter.

impl Error for InferenceError

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.

impl From<InferenceError> for CoreError

fn from(source: InferenceError) -> Self

Converts to this type from the input type.