Fig. 6
From: Using digital archaeology and machine learning to determine sex in finger flutings
Training and testing accuracy of ResNet-18 and EfficientNet-V2-S on virtual images using two different learning rates (1 × 10−5 and 2 × 10−6). The accuracy of both the training and test sets is plotted throughout the training process. Training was conducted for 200 epochs at a learning rate of 1 × 10−5 and 1000 epochs at 2 × 10−6. The Y-axis represents accuracy, calculated as the number of correct predictions divided by the total number of predictions.
