panel_segmentation.panel_train.TrainPanelSegmentationModel.trainingStatistics

TrainPanelSegmentationModel.trainingStatistics(results, mode)

This function prints the training statistics such as training loss and accuracy and validation loss and accuarcy. The dice coefficient was only used for segmentation and not panel classification. We use mode to decide if we should print out dice coefficient.

Parameters

• results (tf.keras.fit_generator History object) – This is the output of the trained classifier. It contains training history.

• mode (int) – If mode = 1, it assumes we want plots for the semantic segmentation and also plots the dice coefficient results. For any other value of mode, it does not show plots of dice coefficients.

Returns

• figures

• Figures based on the model training statistics