A Novel Deep Convolutional Neural Network Based on ResNet-18 and Transfer Learning for Detection of Wood Knot Defects

<div>Training results of the ReSENet-18 model with different optimization algorithms: (a) training loss value and (b) validation accuracy value.</div>

Journal of Sensors

fig18

Figure 18

Figure 18: A Novel Deep Convolutional Neural Network Based on ResNet-18 and Transfer Learning for Detection of Wood Knot Defects 