YOLOv3_TensorFlow icon indicating copy to clipboard operation
YOLOv3_TensorFlow copied to clipboard
verified publisher icon wizyoung

imagenet pre-trained model

Open jhl13 opened this issue 6 years ago • 0 comments

When training the VOC dataset（train 07+12trainval, test 07 test）, the performance of using imagenet pre-trained model instead of using coco is much worse. Has anyone tried it?

jhl13 avatar May 08 '20 08:05 jhl13