mirror of https://github.com/AlexeyAB/darknet.git
2178 lines
23 KiB
INI
2178 lines
23 KiB
INI
[net]
|
|
# Testing
|
|
#batch=1
|
|
#subdivisions=1
|
|
# Training
|
|
batch=64
|
|
subdivisions=64
|
|
width=608
|
|
height=608
|
|
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=sgdr
|
|
sgdr_cycle=1000
|
|
sgdr_mult=2
|
|
steps=4000,6000,8000,9000
|
|
#scales=1, 1, 0.1, 0.1
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=7
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[maxpool]
|
|
size=2
|
|
stride=2
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-2
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
|
|
# Conv 4
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-2
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
|
|
|
|
|
|
### TridentNet - large objects - Start
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
|
|
## Conv 5
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-2
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
dilation=3
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=2048
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=24
|
|
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=1
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
random=0
|
|
|
|
### TridentNet - large objects - End
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
### TridentNet - medium objects - Start
|
|
|
|
[route]
|
|
layers = 165
|
|
|
|
[convolutional]
|
|
share_index=166
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=167
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=168
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=170
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=171
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=172
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=174
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=175
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=176
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=178
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=179
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=180
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=182
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=183
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=184
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=186
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=187
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=188
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
|
|
## Conv 5
|
|
[convolutional]
|
|
share_index=190
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=191
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=192
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-2
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=194
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=195
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=196
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=198
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=199
|
|
dilation=2
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=200
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=2
|
|
|
|
[route]
|
|
layers = -1, 49
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=24
|
|
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=1
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
random=0
|
|
|
|
### TridentNet - medium objects - End
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
### TridentNet - small objects - Start
|
|
|
|
[route]
|
|
layers = 165
|
|
|
|
[convolutional]
|
|
share_index=166
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=167
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=168
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=170
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=171
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=172
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=174
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=175
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=176
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=178
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=179
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=180
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=182
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=183
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=184
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=186
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=187
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=188
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
|
|
## Conv 5
|
|
[convolutional]
|
|
share_index=190
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=191
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=192
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-2
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=194
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=195
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=196
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=198
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=199
|
|
dilation=1
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
share_index=200
|
|
batch_normalize=1
|
|
filters=2048
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=linear
|
|
|
|
[shortcut]
|
|
from=-4
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=4
|
|
|
|
[route]
|
|
layers = -1, 17
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=24
|
|
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=1
|
|
num=12
|
|
jitter=.3
|
|
ignore_thresh = .7
|
|
truth_thresh = 1
|
|
random=0
|
|
|
|
### TridentNet - small objects - End
|
|
|