layer { name: "loss_cls-lx" type: "SoftmaxWithLoss" bottom: "cls_score" bottom: "labels" propagate_down: 1 propagate_down: 0 top: "loss_cls" include { phase: TRAIN } loss_weight: 1 loss_param { ignore_label: -1
when caffe training was loading, it failed with the below message, what does the message, 'arget_blobs.size() == source_layer->blobs().size() (2 vs. 0) Incompatible number of blobs for layer conv2_deconv', thanks. F0718 18:58:23.310828 3...