I'm trying to build a sentence classifier using Caffe, for example the following dataset:
1 -> 'Fell energy at my home'
2 -> 'I liked the city's new buses'
3 -> 'It has a hole in the road in front of my house'
4 -> 'The new public soccer field is perfect'
I have to classify those sentences like: infrastructure, recreation, security and so on.
How can I do this using Caffe? What logic should I use for this? Like labels and to transform my text to lmdb that can be read by Caffe?