UQ_KERAS_UTILS#
This callback is used to adapt the parameter alpha in the abstention loss. |
|
This callback is used to update the parameters of the contamination model. |
|
|
Function to compute abstention loss. |
|
Function to compute abstention loss. |
|
Abstained accuracy: Function to estimate accuracy over the predicted samples after removing the samples where the model is abstaining. |
Abstained accuracy: Function to estimate accuracy over the predicted samples after removing the samples where the model is abstaining. |
|
|
Function to estimate fraction of the samples where the model is abstaining. |
|
Function to estimate accuracy over the ith class prediction. |
Function to estimate accuracy over the class i prediction after removing the samples where the model is abstaining. |
|
Function to estimate fraction of the samples where the model is abstaining in class i. |
|
|
This function generates a categorical representation with a class added for indicating abstention. |
|
This function modifies the last dense layer in the passed Keras model. |
This function computes the r2 for the heteroscedastic model. |
|
This function computes the mean absolute error (mae) for the heteroscedastic model. |
|
This function computes the mean squared error (mse) for the heteroscedastic model. |
|
This function computes the mean log of the variance (log S) for the heteroscedastic model. |
|
This function computes the heteroscedastic loss for the heteroscedastic model. |
|
|
This function computes the quantile loss for a given quantile fraction. |
|
This function computes the quantile loss for the median and low and high quantiles. |
|
This function computes the quantile metric for a given quantile and corresponding output index. |
|
This function adds a column to the training output to store the indices of the corresponding samples in the training set. |
|
Function to compute contamination loss. |
This function computes the mean squared error (mse) for the contamination model. |
|
This function computes the mean absolute error (mae) for the contamination model. |
|
This function computes the r2 for the contamination model. |