When we load the base network such as VGG, is the weight of the pretrained network useful? I think it is meaningless to pretrain the network with our own database. For example, if I want to detect airplanes, I use many airplane slice images to pretrain the network, and then use the trained model as base network of SSD. The method cannot increase detection_eval. Because I didn't find it load the weight of the network in solver.prototxt. Am I right?
When we load the base network such as VGG, is the weight of the pretrained network useful? I think it is meaningless to pretrain the network with our own database. For example, if I want to detect airplanes, I use many airplane slice images to pretrain the network, and then use the trained model as base network of SSD. The method cannot increase detection_eval. Because I didn't find it load the weight of the network in solver.prototxt. Am I right?