[net]
# Testing
#batch=1
#subdivisions=1
# Training
# batch=8 - 12GB CPU-RAM required (increase batch and subdivisions to increase sequense prediction)
batch=8
subdivisions=8
width=544
height=544
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1


track=1
time_steps=16	# for 8GB GPU
#time_steps=7	# for 4GB GPU
augment_speed=3
sequential_subdivisions=8

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
seq_scales=0.5, 1, 0.5, 1

[convolutional]
batch_normalize=1
filters=16
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=1

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky

###########

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[conv_lstm]
batch_normalize=1
size=3
pad=1
output=128
groups=1
peephole=0
bottleneck=1
#shortcut=1
time_normalizer=1.0
lstm_activation=tanh
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


########### to [yolo-3]


[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 8

###########

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[conv_lstm]
batch_normalize=1
size=3
pad=1
output=128
groups=1
peephole=0
bottleneck=1
#shortcut=1
time_normalizer=1.0
lstm_activation=tanh
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

########### to [yolo-2]


[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 6

###########

[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky

[conv_lstm]
batch_normalize=1
size=3
pad=1
output=64
groups=1
peephole=0
bottleneck=1
#shortcut=1
time_normalizer=1.0
lstm_activation=tanh
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

########### [yolo-1]

[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky


[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear

[yolo]
mask = 0,1,2
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=1
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=0
max_delta=5



########### [yolo-2]


[route]
layers = -11

[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky


[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear

[yolo]
mask = 3,4,5
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=1
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=0
max_delta=5



########### [yolo-3]


[route]
layers = -22

[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear



[yolo]
mask = 6,7,8
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=1
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=0
max_delta=5