939 lines
10 KiB
INI
939 lines
10 KiB
INI
[net]
|
|
# Testing
|
|
#batch=1
|
|
#subdivisions=1
|
|
# Training
|
|
batch=64
|
|
subdivisions=32
|
|
width=544
|
|
height=544
|
|
channels=3
|
|
momentum=0.9
|
|
decay=0.0005
|
|
angle=0
|
|
saturation = 1.5
|
|
exposure = 1.5
|
|
hue=.1
|
|
|
|
|
|
learning_rate=0.001
|
|
burn_in=1000
|
|
max_batches = 10000
|
|
|
|
policy=steps
|
|
steps=8000,9000
|
|
scales=.1,.1
|
|
|
|
#policy=sgdr
|
|
#sgdr_cycle=1000
|
|
#sgdr_mult=2
|
|
#steps=4000,6000,8000,9000
|
|
#scales=1, 1, 0.1, 0.1
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=32
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=32
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
######################
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
### SPP ###
|
|
[maxpool]
|
|
stride=1
|
|
size=5
|
|
|
|
[route]
|
|
layers=-2
|
|
|
|
[maxpool]
|
|
stride=1
|
|
size=9
|
|
|
|
[route]
|
|
layers=-4
|
|
|
|
[maxpool]
|
|
stride=1
|
|
size=13
|
|
|
|
[route]
|
|
layers=-1,-3,-5,-6
|
|
|
|
### End SPP ###
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
|
|
|
|
########### to [yolo-3]
|
|
|
|
|
|
|
|
[route]
|
|
layers = -4
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=2
|
|
|
|
[route]
|
|
layers = -1, 61
|
|
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
|
|
########### to [yolo-2]
|
|
|
|
|
|
|
|
|
|
[route]
|
|
layers = -4
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=2
|
|
|
|
[route]
|
|
layers = -1, 36
|
|
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=256
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=256
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
|
|
|
|
########### to [yolo-1]
|
|
|
|
|
|
########### features of different layers
|
|
|
|
|
|
[route]
|
|
layers=1
|
|
|
|
[reorg3d]
|
|
stride=2
|
|
|
|
[route]
|
|
layers=5,-1
|
|
|
|
[reorg3d]
|
|
stride=2
|
|
|
|
[route]
|
|
layers=12,-1
|
|
|
|
[reorg3d]
|
|
stride=2
|
|
|
|
[route]
|
|
layers=37,-1
|
|
|
|
[reorg3d]
|
|
stride=2
|
|
|
|
[route]
|
|
layers=62,-1
|
|
|
|
|
|
|
|
########### [yolo-1]
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=4
|
|
|
|
[route]
|
|
layers = -1,-12
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=256
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=340
|
|
activation=linear
|
|
|
|
|
|
[yolo]
|
|
mask = 0,1,2,3
|
|
anchors = 8,8, 10,13, 16,30, 33,23, 32,32, 30,61, 62,45, 64,64, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
scale_x_y = 1.05
|
|
random=0
|
|
|
|
|
|
|
|
|
|
########### [yolo-2]
|
|
|
|
|
|
[route]
|
|
layers = -7
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=2
|
|
|
|
[route]
|
|
layers = -1,-28
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=340
|
|
activation=linear
|
|
|
|
|
|
[yolo]
|
|
mask = 4,5,6,7
|
|
anchors = 8,8, 10,13, 16,30, 33,23, 32,32, 30,61, 62,45, 64,64, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
scale_x_y = 1.1
|
|
random=0
|
|
|
|
|
|
|
|
########### [yolo-3]
|
|
|
|
[route]
|
|
layers = -14
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[route]
|
|
layers = -1,-43
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=340
|
|
activation=linear
|
|
|
|
|
|
[yolo]
|
|
mask = 8,9,10,11
|
|
anchors = 8,8, 10,13, 16,30, 33,23, 32,32, 30,61, 62,45, 59,119, 80,80, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
scale_x_y = 1.2
|
|
random=0
|