----------------- * ThresholdChecker is updated to compute improvement according to last improved step and not to the best received metric
0.4.11
----------------- * Dense custom layer to support apply norm (configurable to before or after activation) * StatsPrint callback to support printing best confusion matrix when at least one of the metrics is of type ``MetricConfusionMatrixBase`` * Some minor cosmetic changes
0.4.10
----------------- * TransformerEncoderStack to support activation as input * PositionalEncoding to support more than 3 dimensions input
0.4.9
----------------- * Added assert to Attention class (from extensions) when mask is used * Fixed confusion matrix cpu/gpu device error * Better handling on callbacks where apply_on_states=None (apply on all states) * Updated Pipfile
0.4.8
----------------- * Added AbsoluteThresholdChecker & RelativeThresholdChecker classes * ThresholdCheckers can now be used in CallbackMonitor to better define metric tracking
0.4.7
----------------- * Bug fix in case validation samples are empty