SILog

class torch_uncertainty.metrics.SILog(lmbda=1, **kwargs)

The Scale-Invariant Logarithmic Loss metric.

\[\text{SILog} = \frac{1}{N} \sum_{i=1}^{N} \left(\log(y_i) - \log(\hat{y_i})\right)^2 - \left(\frac{1}{N} \sum_{i=1}^{N} \log(y_i) \right)^2\]

where \(N\) is the batch size, \(y_i\) is a tensor of target values and \(\hat{y_i}\) is a tensor of prediction.

Inputs:

• pred: \((N)\)

• target: \((N)\)

Parameters:

• lmbda – The regularization parameter on the variance of error (default 1).

• kwargs – Additional keyword arguments, see Advanced metric settings.

Reference:

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network. David Eigen, Christian Puhrsch, Rob Fergus. NeurIPS 2014. From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation. Jin Han Lee, Myung-Kyu Han, Dong Wook Ko and Il Hong Suh. For the lambda parameter.

compute()

Compute the Scale-Invariant Logarithmic Loss.

update(pred, target)

Update state with predictions and targets.