package owl-base

  1. Overview
  2. Docs
On This Page
  1. Init neuron
  2. Input neuron
  3. Activation neuron
  4. Linear neuron
  5. LinearNoBias neuron
  6. Recurrent neuron
  7. LSTM neuron
  8. GRU neuron
  9. Conv1D neuron
  10. Conv2D neuron
  11. Conv3D neuron
  12. DilatedConv1D neuron
  13. DilatedConv2D neuron
  14. DilatedConv3D neuron
  15. TransposeConv1D neuron
  16. TransposeConv2D neuron
  17. TransposeConv3D neuron
  18. FullyConnected neuron
  19. MaxPool1D neuron
  20. MaxPool2D neuron
  21. AvgPool1D neuron
  22. AvgPool2D neuron
  23. GlobalMaxPool1D neuron
  24. GlobalMaxPool2D neuron
  25. GlobalAvgPool1D neuron
  26. GlobalAvgPool2D neuron
  27. UpSampling1D neuron
  28. UpSampling2D neuron
  29. UpSampling3D neuron
  30. Padding1D neuron
  31. Padding2D neuron
  32. Padding3D neuron
  33. Lambda neuron
  34. LambdaArray neuron
  35. Dropout neuron
  36. Reshape neuron
  37. Flatten neuron
  38. Add neuron
  39. Mul neuron
  40. Dot neuron
  41. Max neuron
  42. Average neuron
  43. Concatenate neuron
  44. Normalisation neuron
  45. GaussianNoise neuron
  46. GaussianDropout neuron
  47. AlphaDropout neuron
  48. Embedding neuron
  49. Masking neuron
  50. Core functions
package owl-base
Legend:
Page
Library
Module
Module type
Parameter
Class
Class type
Source

Module type Owl_neural_neuron_sig.SigSource

Init neuron
Sourcemodule Init : sig ... end
Input neuron
Sourcemodule Input : sig ... end
Activation neuron
Sourcemodule Activation : sig ... end
Linear neuron
Sourcemodule Linear : sig ... end
LinearNoBias neuron
Sourcemodule LinearNoBias : sig ... end
Recurrent neuron
Sourcemodule Recurrent : sig ... end
LSTM neuron
Sourcemodule LSTM : sig ... end
GRU neuron
Sourcemodule GRU : sig ... end
Conv1D neuron
Sourcemodule Conv1D : sig ... end
Conv2D neuron
Sourcemodule Conv2D : sig ... end
Conv3D neuron
Sourcemodule Conv3D : sig ... end
DilatedConv1D neuron
Sourcemodule DilatedConv1D : sig ... end
DilatedConv2D neuron
Sourcemodule DilatedConv2D : sig ... end
DilatedConv3D neuron
Sourcemodule DilatedConv3D : sig ... end
TransposeConv1D neuron
Sourcemodule TransposeConv1D : sig ... end
TransposeConv2D neuron
Sourcemodule TransposeConv2D : sig ... end
TransposeConv3D neuron
Sourcemodule TransposeConv3D : sig ... end
FullyConnected neuron
Sourcemodule FullyConnected : sig ... end
MaxPool1D neuron
Sourcemodule MaxPool1D : sig ... end
MaxPool2D neuron
Sourcemodule MaxPool2D : sig ... end
AvgPool1D neuron
Sourcemodule AvgPool1D : sig ... end
AvgPool2D neuron
Sourcemodule AvgPool2D : sig ... end
GlobalMaxPool1D neuron
Sourcemodule GlobalMaxPool1D : sig ... end
GlobalMaxPool2D neuron
Sourcemodule GlobalMaxPool2D : sig ... end
GlobalAvgPool1D neuron
Sourcemodule GlobalAvgPool1D : sig ... end
GlobalAvgPool2D neuron
Sourcemodule GlobalAvgPool2D : sig ... end
UpSampling1D neuron
Sourcemodule UpSampling1D : sig ... end
UpSampling2D neuron
Sourcemodule UpSampling2D : sig ... end
UpSampling3D neuron
Sourcemodule UpSampling3D : sig ... end
Padding1D neuron
Sourcemodule Padding1D : sig ... end
Padding2D neuron
Sourcemodule Padding2D : sig ... end
Padding3D neuron
Sourcemodule Padding3D : sig ... end
Lambda neuron
Sourcemodule Lambda : sig ... end
LambdaArray neuron
Sourcemodule LambdaArray : sig ... end
Dropout neuron
Sourcemodule Dropout : sig ... end
Reshape neuron
Sourcemodule Reshape : sig ... end
Flatten neuron
Sourcemodule Flatten : sig ... end
Add neuron
Sourcemodule Add : sig ... end
Mul neuron
Sourcemodule Mul : sig ... end
Dot neuron
Sourcemodule Dot : sig ... end
Max neuron
Sourcemodule Max : sig ... end
Average neuron
Sourcemodule Average : sig ... end
Concatenate neuron
Sourcemodule Concatenate : sig ... end
Normalisation neuron
Sourcemodule Normalisation : sig ... end
GaussianNoise neuron
Sourcemodule GaussianNoise : sig ... end
GaussianDropout neuron
Sourcemodule GaussianDropout : sig ... end
AlphaDropout neuron
Sourcemodule AlphaDropout : sig ... end
Embedding neuron
Sourcemodule Embedding : sig ... end
Masking neuron
Sourcemodule Masking : sig ... end
Core functions
Sourcetype neuron =
  1. | Input of Input.neuron_typ
  2. | Linear of Linear.neuron_typ
  3. | LinearNoBias of LinearNoBias.neuron_typ
  4. | Embedding of Embedding.neuron_typ
  5. | LSTM of LSTM.neuron_typ
  6. | GRU of GRU.neuron_typ
  7. | Recurrent of Recurrent.neuron_typ
  8. | Conv1D of Conv1D.neuron_typ
  9. | Conv2D of Conv2D.neuron_typ
  10. | Conv3D of Conv3D.neuron_typ
  11. | DilatedConv1D of DilatedConv1D.neuron_typ
  12. | DilatedConv2D of DilatedConv2D.neuron_typ
  13. | DilatedConv3D of DilatedConv3D.neuron_typ
  14. | TransposeConv1D of TransposeConv1D.neuron_typ
  15. | TransposeConv2D of TransposeConv2D.neuron_typ
  16. | TransposeConv3D of TransposeConv3D.neuron_typ
  17. | FullyConnected of FullyConnected.neuron_typ
  18. | MaxPool1D of MaxPool1D.neuron_typ
  19. | MaxPool2D of MaxPool2D.neuron_typ
  20. | AvgPool1D of AvgPool1D.neuron_typ
  21. | AvgPool2D of AvgPool2D.neuron_typ
  22. | GlobalMaxPool1D of GlobalMaxPool1D.neuron_typ
  23. | GlobalMaxPool2D of GlobalMaxPool2D.neuron_typ
  24. | GlobalAvgPool1D of GlobalAvgPool1D.neuron_typ
  25. | GlobalAvgPool2D of GlobalAvgPool2D.neuron_typ
  26. | UpSampling2D of UpSampling2D.neuron_typ
  27. | Padding2D of Padding2D.neuron_typ
  28. | Dropout of Dropout.neuron_typ
  29. | Reshape of Reshape.neuron_typ
  30. | Flatten of Flatten.neuron_typ
  31. | Lambda of Lambda.neuron_typ
  32. | LambdaArray of LambdaArray.neuron_typ
  33. | Activation of Activation.neuron_typ
  34. | GaussianNoise of GaussianNoise.neuron_typ
  35. | GaussianDropout of GaussianDropout.neuron_typ
  36. | AlphaDropout of AlphaDropout.neuron_typ
  37. | Normalisation of Normalisation.neuron_typ
  38. | Add of Add.neuron_typ
  39. | Mul of Mul.neuron_typ
  40. | Dot of Dot.neuron_typ
  41. | Max of Max.neuron_typ
  42. | Average of Average.neuron_typ
  43. | Concatenate of Concatenate.neuron_typ
    (*

    Types of neuron.

    *)
Sourceval get_in_out_shape : neuron -> int array * int array

Get both input and output shapes of a neuron.

Sourceval get_in_shape : neuron -> int array

Get the input shape of a neuron.

Sourceval get_out_shape : neuron -> int array

Get the output shape of a neuron.

Sourceval connect : int array array -> neuron -> unit

Connect this neuron to others in a neural network.

Sourceval init : neuron -> unit

Initialise the neuron and its parameters.

Sourceval reset : neuron -> unit

Reset the parameters in a neuron.

Sourceval mktag : int -> neuron -> unit

Tag the neuron, used by ``Algodiff`` module.

Sourceval mkpar : neuron -> Optimise.Algodiff.t array

Assemble all the trainable parameters in an array, used by ``Optimise`` module.

Sourceval mkpri : neuron -> Optimise.Algodiff.t array

Assemble all the primal values in an array, used by ``Optimise`` module.

Sourceval mkadj : neuron -> Optimise.Algodiff.t array

Assemble all the adjacent values in an array, used by ``Optimise`` module.

Sourceval update : neuron -> Optimise.Algodiff.t array -> unit

Update trainable parameters in a neuron, used by ``Optimise`` module.

Sourceval load_weights : neuron -> Optimise.Algodiff.t array -> unit

Load both trainable and non-trainable parameters into the neuron.

Sourceval save_weights : neuron -> Optimise.Algodiff.t array

Assemble both trainable and non-trainable parameters of the neuron.

Sourceval copy : neuron -> neuron

Make a deep copy of the neuron and its parameters.

Execute the computation in this neuron.

Sourceval to_string : neuron -> string

Convert the neuron to its string representation. The string is often a summary of the parameters defined in the neuron.

Sourceval to_name : neuron -> string

Return the name of the neuron.