Caffe finetune

在进行Caffe finetune时，需要注意如下事项：
一，从deploy.prototxt到train_val.prototxt时，需要加入训练和测试使用的数据层。
二，在最后需要加上两层 accuary layer 和 loss layer。
三， 需要重要命名原来的最后一层的name。
Because we are predicting 20 classes instead of a 1,000, we do need to change the last layer in the model. Therefore, we change the name of the last layer from fc8 to fc8_flickr in our prototxt. Since there is no layer named that in the bvlc_reference_caffenet, that layer will begin training with random weights.

参考
http://caffe.berkeleyvision.org/gathered/examples/finetune_flickr_style.html

http://www.cnblogs.com/louyihang-loves-baiyan/p/5038758.html