Accelerated by another 5% using FP16/32 Batch-norm for Tensor Cores.

AlexeyAB

2018-04-16 9bae70b22549b68f5cdeece8b6c3b3de00c22714

1
2
3
4
5
classes= 20
train  = /home/pjreddie/data/voc/train.txt
valid  = /home/pjreddie/data/voc/2007_test.txt
names = data/voc.names
backup = /home/pjreddie/backup/