PSegNet: Simultaneous Semantic and Instance Segmentation for Point Clouds of Plants
The changes of losses in the training of PSegNet. From (a–d) are the total loss , the DHL imposed on the midlevel feature layer after DGFMM, the semantic loss , and the instance loss . The -axis of all plots means the number of trained samples, and the -axis is the loss value. Given 3640 training samples and the training batch size at 8, we have 455 samples to be trained in each epoch. When the training stops at 190 epochs, the -axis ends at .