mirror of https://github.com/AlexeyAB/darknet.git
1459 lines
15 KiB
INI
1459 lines
15 KiB
INI
[net]
|
|
# Training
|
|
batch=100
|
|
subdivisions=2
|
|
|
|
label_smooth_eps=0.1
|
|
|
|
# Testing
|
|
# batch=1
|
|
# subdivisions=1
|
|
|
|
height=320
|
|
width=320
|
|
channels=3
|
|
min_crop=320
|
|
max_crop=640
|
|
|
|
mosaic=1
|
|
cutmix=1
|
|
|
|
burn_in=2000
|
|
learning_rate=0.1
|
|
policy=poly
|
|
power=4
|
|
max_batches=1200000
|
|
#max_batches=400000
|
|
momentum=0.9
|
|
decay=0.0005
|
|
|
|
angle=7
|
|
hue=.1
|
|
saturation=.75
|
|
exposure=.75
|
|
aspect=.75
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=40
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -2
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=80
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -1,-13
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -2
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=160
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -1,-49
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -2
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=320
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -1,-49
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1280
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -2
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -1,-25
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1280
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1280
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -2
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -1,-25
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1280
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1280
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -2
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=640
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[route]
|
|
layers = -1,-25
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1600
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=mish
|
|
|
|
[avgpool]
|
|
|
|
[convolutional]
|
|
filters=1000
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[softmax]
|
|
groups=1 |