Enum TensorFormat 

pub enum TensorFormat {
    NCHW,
    NHWC,
    NC1HWC2,
    Undefined,
}

Memory layout of a tensor.

Describes how tensor data is arranged in memory.

• NCHW - channels first. Common in PyTorch. Shape: [batch, channels, height, width].
• NHWC - channels last. Used for RKNN inputs. Shape: [batch, height, width, channels].
• NC1HWC2 - RKNN NPU packed format. Channels are split into blocks. Shape: [batch, c1, height, width, c2]. Use nc1hwc2_to_flat to convert.

Variants

NCHW

Channels first: [N, C, H, W].

NHWC

Channels last: [N, H, W, C]. Standard for RKNN inputs.

NC1HWC2

NPU packed format: [N, c1, H, W, c2]. Common for RKNN outputs on RV1106.

Undefined

Unknown or unsupported format.

Trait Implementations

impl Clone for TensorFormat

fn clone(&self) -> TensorFormat

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TensorFormat

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

Formats the value using the given formatter.

impl From<u32> for TensorFormat

Just an alias for TensorFormat

fn from(v: u32) -> Self

Converts to this type from the input type.

impl PartialEq for TensorFormat

fn eq(&self, other: &TensorFormat) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for TensorFormat

impl Eq for TensorFormat

impl StructuralPartialEq for TensorFormat