Retrain YOLOv2 by Augmenting Data (Rotations)

AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

http://pjreddie.com/darknet/

Other

21.74k stars 7.96k forks source link

Retrain YOLOv2 by Augmenting Data (Rotations) #1808

Open tooskoolforkool opened 6 years ago

tooskoolforkool commented 6 years ago

@AlexeyAB

What happens if I change angle = 0 to, say, angle = 90 in the [net] part of the config file below:

[net]
# Testing
batch=1
subdivisions=1
# Training
# batch=64
# subdivisions=8
height=416
width=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

The reason I am interested in this is that I want to retrain YOLO with rotated data. I need this for satellite imagery.

AlexeyAB commented 6 years ago

Currently angle= isn't supported for Yolo (Detector).

Angle supported only for Classifier.