Enum grpc_vision_svc::image_captioning::ModelVariant

#[non_exhaustive]
pub enum ModelVariant {
    Blip(BlipForConditionalGeneration),
    QuantizedBlip(BlipForConditionalGeneration),
}

Represents different variants of image captioning models.

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.

Blip(BlipForConditionalGeneration)

QuantizedBlip(BlipForConditionalGeneration)

Trait Implementations

impl Clone for ModelVariant

fn clone(&self) -> ModelVariant

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for ModelVariant

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

Formats the value using the given formatter.

impl Module for ModelVariant

fn forward(&self, xs: &Tensor) -> Result<Tensor>

Performs a forward pass for the vision model.

This function takes an input tensor, passes it through the vision model, and returns the resulting tensor.

Arguments

• xs - A reference to the input tensor to be processed by the vision model.

Returns

A Result containing the output tensor if the forward pass is successful, or an error if the forward pass fails.

Errors

Returns an error if the vision model’s forward pass encounters any issues.