mirror of
https://github.com/pjreddie/darknet.git
synced 2023-08-10 21:13:14 +03:00
Fixed densenet201_yolo.cfg - burn_in and poly policy, that changes learning rate
This commit is contained in:
@ -14,11 +14,11 @@ channels=3
|
||||
momentum=0.9
|
||||
decay=0.0005
|
||||
|
||||
learning_rate=0.0001
|
||||
max_batches = 45000
|
||||
policy=steps
|
||||
steps=100,25000,35000
|
||||
scales=10,.1,.1
|
||||
burn_in=1000
|
||||
learning_rate=0.1
|
||||
policy=poly
|
||||
power=4
|
||||
max_batches=1600000
|
||||
|
||||
angle=7
|
||||
hue=.1
|
||||
|
Reference in New Issue
Block a user