Open ameliatqy opened 6 years ago
@ameliatqy I believe I took it from https://github.com/xingwangsfu/caffe-yolo
@gudovskiy Thanks for your reply!
Interesting - because the TinyYOLO deploy file in xingwangsfu is different from yours. Yours has three connected layers at the end while his only has one with batch-norm scale functionalities. Maybe his or yours is an older version of TinyYOLO?
Hey there,
I noticed there is a difference between this repo's TinyYOLO model (yolo_tiny_deploy.prototxt) and the one generated by the code create_yolo_prototxt.py (i.e. the yolo_tiny_deploy.prototxt at xingwangsfu). May I ask where this repo's TinyYOLO model comes from and how can I train it?
Thank you and appreciate your help!