Struct DeformConv2dConfig 

pub struct DeformConv2dConfig {
    pub channels: [usize; 2],
    pub kernel_size: [usize; 2],
    pub stride: [usize; 2],
    pub dilation: [usize; 2],
    pub weight_groups: usize,
    pub offset_groups: usize,
    pub padding: PaddingConfig2d,
    pub bias: bool,
    pub initializer: Initializer,
}

Configuration to create a deformable 2D convolution layer, using the init function.

Fields

channels: [usize; 2]

The number of channels.

kernel_size: [usize; 2]

The size of the kernel.

stride: [usize; 2]

The stride of the convolution.

dilation: [usize; 2]

Spacing between kernel elements.

weight_groups: usize

Controls the connections between input and output channels.

offset_groups: usize

Offset groups.

padding: PaddingConfig2d

The padding configuration.

Warning

Only symmetric padding is currently supported. As such, using Same padding with an even kernel size is not supported as it will not produce the same output size.

bias: bool

If bias should be added to the output.

initializer: Initializer

The type of function used to initialize neural network parameters

Implementations

impl DeformConv2dConfig

pub fn new(channels: [usize; 2], kernel_size: [usize; 2]) -> DeformConv2dConfig

Create a new instance of the config.

impl DeformConv2dConfig

pub fn with_stride(self, stride: [usize; 2]) -> DeformConv2dConfig

The stride of the convolution.

pub fn with_dilation(self, dilation: [usize; 2]) -> DeformConv2dConfig

Spacing between kernel elements.

pub fn with_weight_groups(self, weight_groups: usize) -> DeformConv2dConfig

Controls the connections between input and output channels.

pub fn with_offset_groups(self, offset_groups: usize) -> DeformConv2dConfig

Offset groups.

pub fn with_padding(self, padding: PaddingConfig2d) -> DeformConv2dConfig

The padding configuration.

pub fn with_bias(self, bias: bool) -> DeformConv2dConfig

If bias should be added to the output.

pub fn with_initializer(self, initializer: Initializer) -> DeformConv2dConfig

The type of function used to initialize neural network parameters

impl DeformConv2dConfig

pub fn init<B>(&self, device: &<B as Backend>::Device) -> DeformConv2d<B>

where B: Backend,

Initialize a new DeformConv2d module.

Trait Implementations

impl Clone for DeformConv2dConfig

fn clone(&self) -> DeformConv2dConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Config for DeformConv2dConfig

fn save<P>(&self, file: P) -> Result<(), Error>

where P: AsRef<Path>,

Saves the configuration to a file.

fn load<P>(file: P) -> Result<Self, ConfigError>

where P: AsRef<Path>,

Loads the configuration from a file.

fn load_binary(data: &[u8]) -> Result<Self, ConfigError>

Loads the configuration from a binary buffer.

impl Debug for DeformConv2dConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DeformConv2dConfig

fn deserialize<D>( deserializer: D, ) -> Result<DeformConv2dConfig, <D as Deserializer<'de>>::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for DeformConv2dConfig

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

Formats the value using the given formatter.

impl Serialize for DeformConv2dConfig

fn serialize<S>( &self, serializer: S, ) -> Result<<S as Serializer>::Ok, <S as Serializer>::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.