The streaming_auc keeps accumulating the scores of repeated calls to it, so that you can use it for example to get the auc of several batch runs all acummulated. It does not just calculate the current auc.

In order to use it to get just the current auc, you can reset the local variables it uses (e.g. running tf.initialize_local_variables()) before running it's update operation.

The streaming_auc keeps accumulating the scores of repeated calls to it, so that you can use it, for example, to get the AUC of several batch runs all accumulated. It does not just calculate the current AUC.

In order to use it to get just the current AUC, you can reset the local variables it uses (e.g. running tf.initialize_local_variables()) before running its update operation.