Functions — github.com/AnicetNgrt/jiro-nn

CodeHub MCPcopy Create free account

hub / github.com/AnicetNgrt/jiro-nn / functions

Functions858 in github.com/AnicetNgrt/jiro-nn

⨍ Functions 858◇ Types & classes 90

src/linalg/nalgebra_matrix.rs:243

src/linalg/arrayfire_matrix.rs:284

src/vision/image/nalgebra_image.rs:167

src/vision/image/arrayfire_image.rs:403

src/vision/image/ndarray_image.rs:167

Methodmean_along

(&self, dim: usize)

src/vision/image/nalgebra_image.rs:171

Methodmean_along

(&self, dim: usize)

src/vision/image/arrayfire_image.rs:407

Functionmedian_vector

(vec: &Vec<Scalar>)

src/vec_utils.rs:67

src/linalg/arrayfire_matrix.rs:316

(&self, other: &Self)

src/linalg/ndarray_matrix.rs:227

(&self, other: &Self)

src/linalg/nalgebra_matrix.rs:259

(&self, other: &Self)

src/linalg/arrayfire_matrix.rs:300

(&self, other: &Self)

src/vision/image/nalgebra_image.rs:187

(&self, other: &Self)

src/vision/image/arrayfire_image.rs:423

(&self, other: &Self)

src/vision/image/ndarray_image.rs:187

src/model/full_dense_conv_layer_model.rs:165

src/model/full_direct_conv_layer_model.rs:162

(y_pred: &Matrix, y_true: &Matrix)

src/loss/mse.rs:16

Functionmse_prime

(y_pred: &Matrix, y_true: &Matrix)

src/loss/mse.rs:20

Functionmse_vec

(y_true: &Vec<Scalar>, y_pred: &Vec<Scalar>)

src/loss/mse.rs:6

src/vision/conv_activation/sigmoid.rs:28

src/vision/conv_activation/linear.rs:4

src/vision/conv_activation/tanh.rs:23

src/activation/sigmoid.rs:16

src/activation/linear.rs:4

src/activation/tanh.rs:17

src/activation/softmax.rs:105

src/loss/bce.rs:36

(features: &[Feature])

src/dataset.rs:127

( train_loss: Scalar, test_loss_avg: Scalar, test_loss_std: Scalar, r2: Scalar

src/benchmarking.rs:135

( extracted_feature_config: Box<dyn Fn(&Feature) -> Option<Feature>>, extract_feature: Box<dyn

src/preprocessing/feature_cached.rs:16

src/preprocessing/mod.rs:42

(count: usize, shuffle: bool)

src/preprocessing/sample.rs:11

src/preprocessing/normalize.rs:16

src/preprocessing/square.rs:15

src/preprocessing/log_scale.rs:17

src/preprocessing/map.rs:155

(id_column_name: &str)

src/preprocessing/attach_ids.rs:11

(layers: Vec<Box<dyn NetworkLayer>>)

src/network/mod.rs:21

(parent: NetworkModelBuilder, size: usize)

src/model/full_dense_layer_model.rs:46

(dataset_config: Dataset)

src/model/mod.rs:35

(parent: ConvNetworkModelBuilder, kernels_count: usize, kernels_size: usize)

src/model/full_dense_conv_layer_model.rs:57

(parent: NetworkModelBuilder, in_channels: usize)

src/model/conv_network_model.rs:14

(parent: ConvNetworkModelBuilder, kernels_size: usize)

src/model/full_direct_conv_layer_model.rs:55

src/model/network_model.rs:13

( i: usize, j: usize, weights_optimizer: Optimizers, biases_optimizer: Optimiz

src/layer/dense_layer.rs:25

(dense: DenseLayer, activation: ActivationLayer, dropout: Option<Scalar>)

src/layer/full_layer.rs:22

(layers: Vec<Box<dyn ConvNetworkLayer>>, channels: usize)

src/vision/conv_network.rs:20

(learning_rate: LearningRateSchedule, momentum: Scalar)

src/vision/conv_optimizer/momentum.rs:23

(learning_rate: LearningRateSchedule)

src/vision/conv_optimizer/sgd.rs:28

( learning_rate: LearningRateSchedule, beta1: Scalar, beta2: Scalar, epsilon:

src/vision/conv_optimizer/adam.rs:39

(activation: ConvActivationFn, derivative: ConvActivationFn)

src/vision/conv_activation/mod.rs:21

( nrow: usize, ncol: usize, nchan: usize, nkern: usize, kernels_initia

src/vision/conv_layer/dense_conv_layer.rs:24

( conv: Box<dyn ConvLayer>, activation: ConvActivationLayer, dropout: Option<Scalar>,

src/vision/conv_layer/full_conv_layer.rs:24

( div: usize, )

src/vision/conv_layer/avg_pooling_layer.rs:18

( krows: usize, kcols: usize, in_chans: usize, kernels_initializer: ConvInitia

src/vision/conv_layer/direct_conv_layer.rs:24

src/monitor/mod.rs:72

(ratio: Scalar)

src/trainers/split.rs:30

src/trainers/kfolds.rs:41

( initial_learning_rate: Scalar, decay_steps: Scalar, decay_rate: Scalar, stai

src/learning_rate/inverse_time_decay.rs:15

(boundaries: Vec<usize>, values: Vec<Scalar>)

src/learning_rate/piecewise_constant.rs:12

(activation: ActivationFn, derivative: ActivationFn)

src/activation/mod.rs:31

(loss: LossFn, derivative: LossPrimeFn)

src/loss/mod.rs:34

(learning_rate: LearningRateSchedule, momentum: Scalar)

src/optimizer/momentum.rs:24

(learning_rate: LearningRateSchedule)

src/optimizer/sgd.rs:27

( learning_rate: LearningRateSchedule, beta1: Scalar, beta2: Scalar, epsilon:

src/optimizer/adam.rs:38

Methodnew_empty

src/benchmarking.rs:26

Methodnew_empty

src/datatable.rs:24

Methodnew_grad_dep

(activation: ActivationFn, derivative: GradDepActivationFn)

src/activation/mod.rs:40

Methodout_img_dims_and_channels

( in_rows: usize, in_cols: usize, krows: usize, kcols: usize, kchans:

src/vision/conv_layer/dense_conv_layer.rs:43

Methodout_img_dims_and_channels

( in_rows: usize, in_cols: usize, in_chans: usize, krows: usize, kcols

src/vision/conv_layer/direct_conv_layer.rs:42

Methodpredict_evaluate

`input` has shape `(i,)` where `i` is the number of inputs. `y` has shape `(j,)` where `j` is the number of outputs.

src/network/mod.rs:59

Methodpreds_to_table

Uses the model's dataset configuration to label the prediction's columns and convert it all to a `DataTable` spreadsheet.

src/model/mod.rs:214

src/linalg/nalgebra_matrix.rs:281

src/linalg/arrayfire_matrix.rs:322

Functionr2_score

(y: &Vec<Scalar>, y_hat: &Vec<Scalar>)

src/vec_utils.rs:52

Methodrandom_in_out_samples

( &self, out_columns: &[&str], size: Option<usize>, )

src/datatable.rs:535

Methodrandom_normal

(nrow: usize, ncol: usize, mean: Scalar, std_dev: Scalar)

src/linalg/ndarray_matrix.rs:36

Methodrandom_normal

Creates a matrix with random values following a normal distribution.

src/linalg/nalgebra_matrix.rs:43

Methodrandom_normal

Creates a matrix with random values following a normal distribution.

src/linalg/arrayfire_matrix.rs:51

Methodrandom_normal

( nrow: usize, ncol: usize, nchan: usize, samples: usize, mean: Scalar

src/vision/image/nalgebra_image.rs:29

Methodrandom_normal

( nrow: usize, ncol: usize, nchan: usize, samples: usize, mean: Scalar

src/vision/image/arrayfire_image.rs:71

Methodrandom_normal

( nrow: usize, ncol: usize, nchan: usize, samples: usize, mean: Scalar

src/vision/image/ndarray_image.rs:29

Methodrandom_uniform

(nrow: usize, ncol: usize, min: Scalar, max: Scalar)

src/linalg/ndarray_matrix.rs:29

Methodrandom_uniform

Creates a matrix with random values between min and max (excluded).

src/linalg/nalgebra_matrix.rs:33

Methodrandom_uniform

Creates a matrix with random values between min and max (excluded).

src/linalg/arrayfire_matrix.rs:36

Methodrandom_uniform

( nrow: usize, ncol: usize, nchan: usize, samples: usize, min: Scalar,

src/vision/image/nalgebra_image.rs:18

Methodrandom_uniform

( nrow: usize, ncol: usize, nchan: usize, samples: usize, min: Scalar,

src/vision/image/arrayfire_image.rs:40

Methodrandom_uniform

( nrow: usize, ncol: usize, nchan: usize, samples: usize, min: Scalar,

src/vision/image/ndarray_image.rs:18

src/model/full_dense_conv_layer_model.rs:97

src/model/full_direct_conv_layer_model.rs:94

Methodreplace_with

(value: MapValue)

src/preprocessing/map.rs:68

Methodreplace_with_feature

(feature_name: S)

src/preprocessing/map.rs:76

Methodreplace_with_scalar

(value: Scalar)

src/preprocessing/map.rs:72

Methodreverse_columnswise

(&mut self, data: &DataTable)

src/preprocessing/feature_cached.rs:141

Methodreverse_columnswise

(&mut self, data: &DataTable)

src/preprocessing/one_hot_encode.rs:70

Methodreverse_columnswise

(&mut self, data: &DataTable)

src/preprocessing/extract_months.rs:56

Methodreverse_columnswise

(&mut self, data: &DataTable)

src/preprocessing/filter_outliers.rs:25

Methodreverse_columnswise

(&mut self, data: &DataTable)

src/preprocessing/sample.rs:27

Methodreverse_columnswise

(&mut self, data: &DataTable)

src/preprocessing/normalize.rs:86

← previous next →601–700 of 858, ranked by callers