Struct VisionParameters 

pub struct VisionParameters {
    pub input_size: u32,
    pub embedding_dim: u32,
    pub normalization: String,
    pub image_formats: Vec<String>,
}

Vision encoder parameters.

Captures everything needed to feed an image into an ONNX vision encoder: spatial input size, output embedding dimensionality, the normalization recipe (e.g., “clip”, “imagenet”, “siglip”), and the list of accepted image container formats. Used by VisionRuntime and the catalog-driven loader.

Fields

input_size: u32

Square input edge in pixels (e.g., 224, 256, 336, 384).

embedding_dim: u32

Output embedding dimensionality (e.g., 512 for CLIP B/32, 1024 for DINOv2 large).

normalization: String

Normalization recipe key — "clip" | "imagenet" | "siglip".

image_formats: Vec<String>

Accepted image container formats (e.g., ["png", "jpeg", "webp"]).

Trait Implementations

impl Clone for VisionParameters

fn clone(&self) -> VisionParameters

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for VisionParameters

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for VisionParameters

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for VisionParameters

impl PartialEq for VisionParameters

fn eq(&self, other: &VisionParameters) -> 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 Serialize for VisionParameters

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for VisionParameters