Struct leaf::weight::WeightConfig
[−]
[src]
pub struct WeightConfig { pub name: String, pub share_mode: DimCheckMode, pub lr_mult: Option<f32>, pub decay_mult: Option<f32>, pub filler: Option<FillerType>, }
Specifies training configuration for a weight blob.
Fields
name | The name of the weight blob -- useful for sharing weights among layers, but never required otherwise. To share a weight between two layers, give it a (non-empty) name. Default: "" |
share_mode | Whether to require shared weights to have the same shape, or just the same count Default: DimCheckMode::Strict |
lr_mult | The multiplier on the global learning rate for this parameter. Default: 1.0f32 |
decay_mult | The multiplier on the global weight decay for this parameter. Default: 1.0f32 |
filler | The filler that initializes the weights in the weight blob. Default: None |
Methods
impl WeightConfig
fn check_dimensions<T>(&self, tensor_one: &SharedTensor<T>, tensor_two: &SharedTensor<T>, param_name: String, owner_name: String, layer_name: String) -> Result<(), String>
Checks dimensions of two blobs according to the share_mode
.
Returns an error if there is a count/shape mismatch.
fn lr_mult(&self) -> f32
The multiplier on the global learning rate for this weight blob.
fn decay_mult(&self) -> f32
The multiplier on the global weight decay for this weight blob.