Skip to main content
. 2020 Sep 2;11:534853. doi: 10.3389/fpls.2020.534853

Table 2.

Mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE) for 10 sets of training images for a sorghum panicle detection and counting algorithm using a U-Net Convolutional Neural Networks model on unmanned aerial system images.

No. of Images 100 200 300 400 500 600 700 800 900 1000
MAE 53.1 35.2 28.1 27.2 23.7 19.6 16.9 11.4 9.9 6.3
MAPE 0.41 0.25 0.20 0.21 0.18 0.15 0.13 0.09 0.07 0.05
RMSE 7.3 5.9 5.3 5.2 4.9 4.4 4.1 3.4 3.2 2.5