Open spinlud opened 4 years ago
Thank you @AlexeyAB, exactly what I was looking for! Hope you don't mind, I have some doubts about the following:
scale_x_y
, resize
and jitter
, what is the difference?angle=0
means that no rotation augmentation is added, is this right?adversarial_lr=1.0
this is very fascinating and mysterious, could you elaborate a bit what does it mean Changes all detected objects to make it unlike themselves from neural network point of view
? In practice what happens?hue
, saturation
, mosaic
, blur
, etc) must be placed in the [net]
layer, correct?@spinlud Here is how I understand these params:
Thanks a lot!
Hi guys! I am using
yolov3-tiny
andyolov4-tiny
to train a custom model. For my current task I don't need any rotation, horizontal/vertical flip and skewness on the training images. Do I need to change anything in the.cfg
file to disable these types of data augmentation or are they already disabled?Looking for example inside the
yolov4-tiny.cfg
file I seeangle=0
, does this mean that rotation augmentation is disabled? And what about horizontal/vertical flip and skewness, do I need to do anything? Is there a list of the parameters used inyolo
with a description about what they do?Thanks for any info!