Struct SamEncoder 

pub struct SamEncoder<B: Backend> { /* private fields */ }

SAM vision encoder for the DeepSeek-OCR DeepEncoder architecture.

Implements the complete SAM encoding pipeline:

1. Patch embedding: Image → patches
2. Position embedding: Add learned position encodings
3. Transformer blocks: Window/global attention processing
4. Neck: Project to output channels
5. Compression: 16× spatial reduction via convolutional layers

Compression Pipeline

For a 1024×1024 image with 16×16 patches:

• Input: [B, 3, 1024, 1024]
• After patch embed: [B, 768, 64, 64] (1024/16 = 64)
• After transformers: [B, 768, 64, 64]
• After neck: [B, 256, 64, 64]
• After comp1: [B, 512, 32, 32] (stride=2)
• After comp2: [B, 1024, 16, 16] (stride=2)
• Result: 16× compression (64² → 16² tokens)

Implementations

impl<B: Backend> SamEncoder<B>

pub fn new(config: &SamConfig, device: &B::Device) -> Self

Creates a new SAM encoder from configuration.

Arguments

• config - SAM configuration (see SamConfig)
• device - Device to create the model on

Example

let config = SamConfig::base();
let encoder = SamEncoder::new(&config, &device);

pub fn forward(&self, x: Tensor<B, 4>) -> Tensor<B, 4>

Encodes an image into compressed vision features.

Arguments

• x - Input image tensor

Shape

• Input: [B, 3, H, W]
• Output: [B, 1024, H/P/4, W/P/4] where P is patch_size

For default settings (patch_size=16, 16× compression):

• 1024×1024 image → [B, 1024, 16, 16] (256 tokens)
• 512×512 image → [B, 1024, 8, 8] (64 tokens)

Example

let image = Tensor::zeros(, &device);[1]
let features = encoder.forward(image);
// Shape:  = 256 vision tokens[2][1]

Trait Implementations

impl<B> AutodiffModule<B> for SamEncoder<B>

where B: AutodiffBackend + Backend, <B as AutodiffBackend>::InnerBackend: Backend,

type InnerModule = SamEncoder<<B as AutodiffBackend>::InnerBackend>

Inner module without auto-differentiation.

fn valid(&self) -> Self::InnerModule

Get the same module, but on the inner backend without auto-differentiation.

impl<B: Backend> Clone for SamEncoder<B>

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<B: Debug + Backend> Debug for SamEncoder<B>

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

Formats the value using the given formatter.

impl<B: Backend> Display for SamEncoder<B>

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

Formats the value using the given formatter.

impl<B: Backend> Module<B> for SamEncoder<B>

type Record = SamEncoderRecord<B>

Type to save and load the module.

fn load_record(self, record: Self::Record) -> Self

Load the module state from a record.

fn into_record(self) -> Self::Record

Convert the module into a record containing the state.

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules.

fn visit<Visitor: ModuleVisitor<B>>(&self, visitor: &mut Visitor)

Visit each tensor parameter in the module with a visitor.

fn map<Mapper: ModuleMapper<B>>(self, mapper: &mut Mapper) -> Self

Map each tensor parameter in the module with a mapper.

fn collect_devices(&self, devices: Devices<B>) -> Devices<B>

Return all the devices found in the underneath module tree added to the given vector without duplicates.

fn to_device(self, device: &B::Device) -> Self

Move the module and all of its sub-modules to the given device.

fn fork(self, device: &B::Device) -> Self

Fork the module and all of its sub-modules to the given device.

fn devices(&self) -> Vec<<B as Backend>::Device>

Return all the devices found in the underneath module tree without duplicates.

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad.

fn save_file<FR, PB>( self, file_path: PB, recorder: &FR, ) -> Result<(), RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Save the module to a file using the provided file recorder.

fn load_file<FR, PB>( self, file_path: PB, recorder: &FR, device: &<B as Backend>::Device, ) -> Result<Self, RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Load the module from a file using the provided file recorder.

fn quantize_weights(self, quantizer: &mut Quantizer) -> Self

Quantize the weights of the module.

impl<B: Backend> ModuleDisplay for SamEncoder<B>

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings.

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module.

fn custom_content(&self, _content: Content) -> Option<Content>

Custom attributes for the module.

impl<B: Backend> ModuleDisplayDefault for SamEncoder<B>

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes.

fn num_params(&self) -> usize

Gets the number of the parameters of the module.