AurocMetricPyTorch

class AurocMetricPyTorch[source]

Metric to Calculate AuROC

Deprecated since version 0.1: AurocMetricPyTorch will be removed in next release and is deprecated in favor of trixi.logging Modules

Warning

AurocMetricPyTorch will be removed in next release

forward(outputs: torch.Tensor, targets: torch.Tensor)[source]

Actual AuROC calculation

Parameters
Returns

auroc value

Return type

torch.Tensor

AccurarcyMetricPyTorch

class AccuracyMetricPyTorch[source]

Metric to Calculate Accuracy

Deprecated since version 0.1: AccuracyMetricPyTorch will be removed in next release and is deprecated in favor of trixi.logging Modules

Warning

class:AccuracyMetricPyTorch will be removed in next release

forward(outputs: torch.Tensor, targets: torch.Tensor)[source]

Actual accuracy calcuation

Parameters
Returns

accuracy value

Return type

torch.Tensor

pytorch_batch_to_numpy

pytorch_batch_to_numpy(tensor: torch.Tensor)[source]

Utility Function to cast a whole PyTorch batch to numpy

Parameters

tensor (torch.Tensor) – the batch to convert

Returns

the converted batch

Return type

np.ndarray

pytorch_tensor_to_numpy

pytorch_tensor_to_numpy(tensor: torch.Tensor)[source]

Utility Function to cast a single PyTorch Tensor to numpy

Parameters

tensor (torch.Tensor) – the tensor to convert

Returns

the converted tensor

Return type

np.ndarray

float_to_pytorch_tensor

float_to_pytorch_tensor(f: float)[source]

Converts a single float to a PyTorch Float-Tensor

Parameters

f (float) – float to convert

Returns

converted float

Return type

torch.Tensor

create_optims_default_pytorch

create_optims_default_pytorch(model, optim_cls, **optim_params)[source]

Function to create a optimizer dictionary (in this case only one optimizer for the whole network)

Parameters
  • model (AbstractPyTorchNetwork) – model whose parameters should be updated by the optimizer

  • optim_cls – Class implementing an optimization algorithm

  • **optim_params – Additional keyword arguments (passed to the optimizer class

Returns

dictionary containing all created optimizers

Return type

dict

create_optims_gan_default_pytorch

create_optims_gan_default_pytorch(model, optim_cls, **optim_params)[source]

Function to create a optimizer dictionary (in this case two optimizers: One for the generator, one for the discriminator)

Parameters
  • model (AbstractPyTorchNetwork) – model whose parameters should be updated by the optimizer

  • optim_cls – Class implementing an optimization algorithm

  • optim_params – Additional keyword arguments (passed to the optimizer class

Returns

dictionary containing all created optimizers

Return type

dict

create_optims_default_tf

create_optims_default_tf(optim_cls, **optim_params)[source]

Function to create a optimizer dictionary (in this case only one optimizer)

Parameters
  • optim_cls – Class implementing an optimization algorithm

  • **optim_params – Additional keyword arguments (passed to the optimizer class)

Returns

dictionary containing all created optimizers

Return type

dict