You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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!
The text was updated successfully, but these errors were encountered:
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?
@ameliatqy I'll try to check if have time. But I remember I took the weight file from the older commit of darknet Yolo repo to match this protobuf. Did you check whether mine matches the official Movidius NCS Yolo repo?
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!
The text was updated successfully, but these errors were encountered: