Skip to main content
. 2017 Dec 28;4(1):120–131. doi: 10.1021/acscentsci.7b00512

Figure 9.

Figure 9

Different training strategies on the Staphylococcus aureus data set with 1000 training and 6051 test examples. Fine-tuning the pretrained model performs better than training from scratch (lower test loss [cross entropy] is better).