Adamdad / keras-YOLOv3-mobilenet

I transfer the backend of yolov3 into Mobilenetv1,VGG16,ResNet101 and ResNeXt101

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

when change the size of input image ,what need to change on train?? the anchor size??

bobo12138 opened this issue · comments

when change the size of input image ,what need to change on train?? the anchor size??
commented

if you train myself datas ,you only exchang to train.py 25line input_image ,this size must multiple of 32,
dataset setup tell me ,we help you

1.i use my own datas to get a new anchor file
but i do not find the size of input image in kmeans.py(the train size is 320*320)

  1. i trained with 3 types of cars, how i set the cluster_number to make train faster?