Struct Conv2d

pub struct Conv2d {
    pub weight: Param<Array>,
    pub bias: Param<Option<Array>>,
    pub padding: (i32, i32),
    pub stride: (i32, i32),
}

Applies a 2-dimensional convolution over the multi-channel input image.

The channels are expected to be last i.e. the input shape should be NHWC where:

• N is the batch dimension
• H is the input image height
• W is the input image width
• C is the number of input channels

Fields

weight: Param<Array>

The weight of the convolution layer.

bias: Param<Option<Array>>

The bias of the convolution layer.

padding: (i32, i32)

Padding. Default to (0, 0) if not specified.

stride: (i32, i32)

Stride. Default to (1, 1) if not specified.

Implementations

impl Conv2d

pub fn new( input_channels: impl Into<i32>, output_channels: impl Into<i32>, kernel_size: impl Into<SingleOrPair<i32>>, ) -> Result<Self, <<Self as Buildable>::Builder as Builder<Self>>::Error>

Creates a new instance of Conv2d.

impl Conv2d

pub const DEFAULT_BIAS: bool = true

Default value for with_bias if not specified.

pub const DEFAULT_PADDING: SingleOrPair = _

Default value for padding if not specified.

pub const DEFAULT_STRIDE: SingleOrPair = _

Default value for stride if not specified.

Trait Implementations

impl Buildable for Conv2d

type Builder = Conv2dBuilder

The builder type for this buildable type

impl Builder<Conv2d> for Conv2dBuilder

type Error = Exception

Error with building

fn build(self) -> Result<Conv2d, Self::Error>

Build the type

impl Clone for Conv2d

fn clone(&self) -> Conv2d

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Conv2d

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

Formats the value using the given formatter.

impl Module<&Array> for Conv2d

type Error = Exception

Error type for the module.

type Output = Array

Output type of the module.

fn forward(&mut self, x: &Array) -> Result<Array, Self::Error>

Forward pass of the module.

fn training_mode(&mut self, _: bool)

Set whether the module is in training mode.

impl ModuleParameters for Conv2d

fn freeze_parameters(&mut self, recursive: bool)

Freeze all parameters in the module.

fn unfreeze_parameters(&mut self, recursive: bool)

Unfreeze all parameters in the module.

fn parameters(&self) -> ModuleParamRef<'_>

Get references to the module parameters.

fn parameters_mut(&mut self) -> ModuleParamMut<'_>

Get mutable references to the module parameters.

fn trainable_parameters(&self) -> ModuleParamRef<'_>

Get references to the trainable parameters. A parameter is trainable if it is NOT frozen.

fn all_frozen(&self) -> Option<bool>

Check if all parameters in the module are frozen. Returns None if there are no parameters.

fn any_frozen(&self) -> Option<bool>

Check if any parameter in the module is frozen. Returns None if there are no parameters.

fn update(&mut self, parameters: ModuleParam)

Update the module parameters.

fn update_flattened(&mut self, flattened_parameters: FlattenedModuleParam)

Update the module parameters from a flattened representation.