CAFFE for darknet
Reference
You Only Look Once: Unified, Real-Time Object detection http://arxiv.org/abs/1506.02640
YOLO9000: Better, Faster, Stronger https://arxiv.org/abs/1612.08242
Data preparation
Prepare data lsit just like the way of original darkenet
No need to generate lmdbs as we directly use raw images in the data list to train
Version
Both v1 & v2 supported