Cannot copy param 0 weights from layer ‘loss1/fc’; shape mismatch

在转换googlenet模型时候总是出现这个问题，困扰 好久了，百度上找也找不到解决办法，今天终于解决了
ERROR：Cannot copy param 0 weights from layer ‘loss1/fc’; shape mismatch.
Source param shape is 1 1 1024 2048 (2097152);
target param shape is 1024 4608 (4718592).
To learn this layer’s parameters from scratch rather than copying from a saved net, rename the layer.

只需要找到deploy.prototxt文件，打开后找到loss1/fc出现的地方，将名字重新命名即可，后来我改完后运行发现loss2/fc同样也是需要修改的，重新命名之后进行量化操作和模型转化操作就成功了，超级开心！！！