Validation metrics for our training of CMUDeeplens. All the datasets are balanced. Left: Minimisation of the loss function during training. The dotted line marks the epoch with the best validation loss. Right: Receiver operating characteristic (ROC) curves for the selected model. The area under the curve is 0.9993, 0.9992, and 0.9992 for the training, validation, and test datasets, respectively. The ‘+’ marks the values at the classification threshold 0.9.