怎样用自己的数据集对caffe训练好的model进行fineture(当类别数量不一致时)

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

e.g:

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.