Module `ml4opf.models.pca_nn.pca_nn`

Classes

class ACPCANN (opfmodel: OPFModel, slices: list[slice], pca_w: torch.Tensor, pca_mu: torch.Tensor, optimizer: str = 'adam', loss: str = 'mse', hidden_sizes: list[int] = [100, 100], activation: str = 'relu', boundrepair: str = 'none', learning_rate: float = 0.001, weight_init_seed: int = 42)

Browse git

Hooks to be used in LightningModule.

Ancestors

PCANN
ACBasicNN
BasicNN
pytorch_lightning.core.module.LightningModule
lightning_fabric.utilities.device_dtype_mixin._DeviceDtypeModuleMixin
pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin
pytorch_lightning.core.hooks.ModelHooks
pytorch_lightning.core.hooks.DataHooks
pytorch_lightning.core.hooks.CheckpointHooks
torch.nn.modules.module.Module

Inherited members

PCANN:
- configure_optimizers
- forward
- test_step
- training_step
- validation_step

class ACPCANeuralNet (config: dict, problem: OPFProblem)

Browse git

A feed-forward neural network with a PCA layer at the end. The PCA is computed on initialization using the training set.

Ancestors

Class variables

var model : ACPCANN

Inherited members

PCANeuralNet:
- evaluate_model
- load_from_checkpoint
- model_cls
- predict
- save_checkpoint

class DCPCANN (opfmodel: OPFModel, slices: list[slice], pca_w: torch.Tensor, pca_mu: torch.Tensor, optimizer: str = 'adam', loss: str = 'mse', hidden_sizes: list[int] = [100, 100], activation: str = 'relu', boundrepair: str = 'none', learning_rate: float = 0.001, weight_init_seed: int = 42)

Browse git

Hooks to be used in LightningModule.

Ancestors

PCANN
DCBasicNN
BasicNN
pytorch_lightning.core.module.LightningModule
lightning_fabric.utilities.device_dtype_mixin._DeviceDtypeModuleMixin
pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin
pytorch_lightning.core.hooks.ModelHooks
pytorch_lightning.core.hooks.DataHooks
pytorch_lightning.core.hooks.CheckpointHooks
torch.nn.modules.module.Module

Inherited members

PCANN:
- configure_optimizers
- forward
- test_step
- training_step
- validation_step

class DCPCANeuralNet (config: dict, problem: OPFProblem)

Browse git

A feed-forward neural network with a PCA layer at the end. The PCA is computed on initialization using the training set.

Ancestors

Class variables

var model : DCPCANN

Inherited members

PCANeuralNet:
- evaluate_model
- load_from_checkpoint
- model_cls
- predict
- save_checkpoint

class EDPCANN (opfmodel: OPFModel, slices: list[slice], pca_w: torch.Tensor, pca_mu: torch.Tensor, optimizer: str = 'adam', loss: str = 'mse', hidden_sizes: list[int] = [100, 100], activation: str = 'relu', boundrepair: str = 'none', learning_rate: float = 0.001, weight_init_seed: int = 42)

Browse git

Hooks to be used in LightningModule.

Ancestors

PCANN
EDBasicNN
BasicNN
pytorch_lightning.core.module.LightningModule
lightning_fabric.utilities.device_dtype_mixin._DeviceDtypeModuleMixin
pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin
pytorch_lightning.core.hooks.ModelHooks
pytorch_lightning.core.hooks.DataHooks
pytorch_lightning.core.hooks.CheckpointHooks
torch.nn.modules.module.Module

Inherited members

PCANN:
- configure_optimizers
- forward
- test_step
- training_step
- validation_step

class EDPCANeuralNet (config: dict, problem: OPFProblem)

Browse git

A feed-forward neural network with a PCA layer at the end. The PCA is computed on initialization using the training set.

Ancestors

Class variables

var model : EDPCANN

Inherited members

PCANeuralNet:
- evaluate_model
- load_from_checkpoint
- model_cls
- predict
- save_checkpoint

class InversePCALayer (pca_w: torch.Tensor, pca_mu: torch.Tensor)

Browse git

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will also have their parameters converted when you call :meth:to, etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Ancestors

torch.nn.modules.module.Module

Methods

def forward(self, x: torch.Tensor) ‑> torch.Tensor: Browse git

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the :class:Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class PCANN (opfmodel: OPFModel, slices: list[slice], pca_w: torch.Tensor, pca_mu: torch.Tensor, optimizer: str = 'adam', loss: str = 'mse', hidden_sizes: list[int] = [100, 100], activation: str = 'relu', boundrepair: str = 'none', learning_rate: float = 0.001, weight_init_seed: int = 42)

Browse git

Hooks to be used in LightningModule.

Ancestors

BasicNN
pytorch_lightning.core.module.LightningModule
lightning_fabric.utilities.device_dtype_mixin._DeviceDtypeModuleMixin
pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin
pytorch_lightning.core.hooks.ModelHooks
pytorch_lightning.core.hooks.DataHooks
pytorch_lightning.core.hooks.CheckpointHooks
torch.nn.modules.module.Module

Methods

def make_network(self, pca_w: torch.Tensor, pca_mu: torch.Tensor): Browse git

Inherited members

BasicNN:
- configure_optimizers
- forward
- test_step
- training_step
- validation_step

class PCANeuralNet (config: dict, problem: OPFProblem)

Browse git

A feed-forward neural network with a PCA layer at the end. The PCA is computed on initialization using the training set.

Ancestors

Subclasses

ACPCANeuralNet
DCPCANeuralNet
EDPCANeuralNet
SOCPCANeuralNet

Class variables

var model : PCANN

Methods

def make_training_model(self, force_new_model=False): Browse git

Inherited members

BasicNeuralNet:
- evaluate_model
- load_from_checkpoint
- model_cls
- predict
- save_checkpoint

class SOCPCANN (opfmodel: OPFModel, slices: list[slice], pca_w: torch.Tensor, pca_mu: torch.Tensor, optimizer: str = 'adam', loss: str = 'mse', hidden_sizes: list[int] = [100, 100], activation: str = 'relu', boundrepair: str = 'none', learning_rate: float = 0.001, weight_init_seed: int = 42)

Browse git

Hooks to be used in LightningModule.

Ancestors

PCANN
SOCBasicNN
BasicNN
pytorch_lightning.core.module.LightningModule
lightning_fabric.utilities.device_dtype_mixin._DeviceDtypeModuleMixin
pytorch_lightning.core.mixins.hparams_mixin.HyperparametersMixin
pytorch_lightning.core.hooks.ModelHooks
pytorch_lightning.core.hooks.DataHooks
pytorch_lightning.core.hooks.CheckpointHooks
torch.nn.modules.module.Module

Inherited members

PCANN:
- configure_optimizers
- forward
- test_step
- training_step
- validation_step

class SOCPCANeuralNet (config: dict, problem: OPFProblem)

Browse git

A feed-forward neural network with a PCA layer at the end. The PCA is computed on initialization using the training set.

Ancestors

Class variables

var model : SOCPCANN

Inherited members

PCANeuralNet:
- evaluate_model
- load_from_checkpoint
- model_cls
- predict
- save_checkpoint