torchtraining.metrics.regression¶

class torchtraining.metrics.regression.AbsoluteError(reduction=<built-in method mean of type object>)[source]¶

Absolute error between outputs and targets.

Parameters: reduction (Callable(torch.Tensor) -> Any, optional) – One argument callable getting torch.Tensor and returning argument after specified reduction. Default: torch.mean (mean across batch, user can use torchtraining.savers.Mean to get mean across iterations/epochs).

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: If reduction is left as default mean is taken and single value returned. Otherwise whatever reduction returns.
Return type: torch.Tensor

class torchtraining.metrics.regression.AdjustedR2(p: int)[source]¶

Adjusted R2 score between outputs and targets.

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: Scalar tensor
Return type: torch.Tensor

class torchtraining.metrics.regression.MaxError[source]¶

Maximum error between outputs and targets.

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: Scalar tensor
Return type: torch.Tensor

class torchtraining.metrics.regression.R2[source]¶

R2 score between outputs and targets.

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: Scalar tensor
Return type: torch.Tensor

class torchtraining.metrics.regression.RegressionOfSquares(reduction=<built-in method sum of type object>)[source]¶

Regression of squares between outputs and targets.

Parameters: reduction (Callable, optional) – One argument callable getting torch.Tensor and returning torch.Tensor. Default: torch.sum (sum of all elements, user can use torchtraining.savers.Sum to get sum across iterations/epochs).

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: If reduction is left as default sum is taken and single value returned. Otherwise whatever reduction returns.
Return type: torch.Tensor

class torchtraining.metrics.regression.SquaredError(reduction=<built-in method mean of type object>)[source]¶

Squared error between outputs and targets.

Parameters: reduction (Callable(torch.Tensor) -> Any, optional) – One argument callable getting torch.Tensor and returning argument after specified reduction. Default: torch.mean (mean across batch, user can use torchtraining.savers.Mean to get mean across iterations/epochs).

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: If reduction is left as default mean is taken and single value returned. Otherwise whatever reduction returns.
Return type: torch.Tensor

class torchtraining.metrics.regression.SquaredLogError(reduction=<built-in method mean of type object>)[source]¶

Squared log error between outputs and targets.

Parameters: reduction (Callable(torch.Tensor) -> Any, optional) – One argument callable getting torch.Tensor and returning argument after specified reduction. Default: torch.mean (mean across batch, user can use torchtraining.savers.Mean to get mean across iterations/epochs).

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: If reduction is left as default mean is taken and single value returned. Otherwise whatever reduction returns.
Return type: torch.Tensor

class torchtraining.metrics.regression.SquaresOfResiduals(reduction=<built-in method sum of type object>)[source]¶

Square of residuals between outputs and targets.

Parameters: reduction (Callable, optional) – One argument callable getting torch.Tensor and returning torch.Tensor. Default: torch.sum (sum of all elements, user can use torchtraining.savers.Sum to get sum across iterations/epochs).

forward(data)[source]¶

Parameters: data (Tuple[torch.Tensor, torch.Tensor]) – Tuple containing outputs from neural network and regression targets. outputs should be of shape $(N, *)$ , where $N$ is the number of samples. Should contain floating point values. targets should be in the same shape outputs and be of float data type as well.
Returns: If reduction is left as default sum is taken and single value returned. Otherwise whatever reduction returns.
Return type: torch.Tensor

class torchtraining.metrics.regression.TotalOfSquares(reduction=<built-in method sum of type object>)[source]¶

Total of squares of single tensor.

Parameters: reduction (Callable, optional) – One argument callable getting torch.Tensor and returning torch.Tensor. Default: torch.sum (sum of all elements, user can use torchtraining.savers.Sum to get sum across iterations/epochs).

forward(data)[source]¶

Parameters: data (torch.Tensor) – Tensor containing float data of any shape. Usually targets.
Returns: If reduction is left as default {} is taken and single value returned. Otherwise whatever reduction returns.
Return type: torch.Tensor