c40826179b
2.Provide more trained models with different input resoulution.
817 lines
9.4 KiB
INI
817 lines
9.4 KiB
INI
[net]
|
|
batch=16
|
|
subdivisions=1
|
|
width=864
|
|
height=480
|
|
embedding_dim=512
|
|
channels=3
|
|
|
|
[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
|
|
|
|
[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
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=24
|
|
activation=linear
|
|
|
|
######### embedding ###########
|
|
[route]
|
|
layers = -3
|
|
|
|
[convolutional]
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=$embedding_dim
|
|
activation=linear
|
|
|
|
[route]
|
|
layers = -3, -1
|
|
###############################
|
|
|
|
|
|
[yolo]
|
|
mask = 8,9,10,11
|
|
anchors = 6,19, 9,27, 13,38, 18,54, 25,76, 36,107, 51,152, 71,215, 102,305, 143, 429, 203,508, 407,508
|
|
classes=1
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
random=1
|
|
|
|
|
|
[route]
|
|
layers = -7
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=2
|
|
|
|
[route]
|
|
layers = -1, 61
|
|
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=24
|
|
activation=linear
|
|
|
|
######### embedding ###########
|
|
[route]
|
|
layers = -3
|
|
|
|
[convolutional]
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=$embedding_dim
|
|
activation=linear
|
|
|
|
[route]
|
|
layers = -3, -1
|
|
###############################
|
|
|
|
[yolo]
|
|
mask = 4,5,6,7
|
|
anchors = 6,19, 9,27, 13,38, 18,54, 25,76, 36,107, 51,152, 71,215, 102,305, 143, 429, 203,508, 407,508
|
|
classes=1
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
random=1
|
|
|
|
|
|
|
|
[route]
|
|
layers = -7
|
|
|
|
[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
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=256
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=24
|
|
activation=linear
|
|
|
|
|
|
|
|
######### embedding ###########
|
|
[route]
|
|
layers = -3
|
|
|
|
[convolutional]
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=$embedding_dim
|
|
activation=linear
|
|
|
|
[route]
|
|
layers = -3, -1
|
|
###############################
|
|
|
|
[yolo]
|
|
mask = 0,1,2,3
|
|
anchors = 6,19, 9,27, 13,38, 18,54, 25,76, 36,107, 51,152, 71,215, 102,305, 143, 429, 203,508, 407,508
|
|
classes=1
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
random=1
|