Check failed: outer_num_ * inner_num_ == bottom[1]->count() (497025 vs. 504100) Number of labels must match number of predictions; e.g., if softmax axis == 1 and prediction shape is (N, C, H, W), label count (number of labels) must be N*H*W, with integer values in {0, 1, ..., C-1}.
问题大概是说,prediction 与label的shape不一致,bottom[1]->count()就是说的label的count等于504100,prediction的outer_num_ * inner_num_等于497025,也就是说label与prediction不一致。
解决办法:需要去理解每一层的网络的输出,分析是哪一层的输出导致出现的问题。
参考链接:
https://blog.youkuaiyun.com/qq_30024069/article/details/85312170
01-22
1845
