Triain YOLO to detect soy milk

soy-milk.data

classes= 1
train  = data/soy-milk_train.txt
valid  = data/soy-milk_test.txt
names =  data/soy-milk.names
backup = backup

soy-milk.names

soy-milk

soy-milk1.txt

0 0.441797 0.581250 0.636719 0.323611

(this is just an example of box file created by Yolo-mark)

soy-milk_test.txt

data/soy-milk/soy-milk_1.jpg
data/soy-milk/soy-milk_2.jpg
data/soy-milk/soy-milk_3.jpg
data/soy-milk/soy-milk_4.jpg
data/soy-milk/soy-milk_5.jpg
data/soy-milk/soy-milk_6.jpg
data/soy-milk/soy-milk_7.jpg
data/soy-milk/soy-milk_8.jpg
data/soy-milk/soy-milk_9.jpg

soy-milk_train.txt

data/soy-milk/soy-milk_10.jpg
data/soy-milk/soy-milk_11.jpg
data/soy-milk/soy-milk_12.jpg
data/soy-milk/soy-milk_13.jpg
data/soy-milk/soy-milk_14.jpg
data/soy-milk/soy-milk_15.jpg
data/soy-milk/soy-milk_16.jpg
data/soy-milk/soy-milk_17.jpg
data/soy-milk/soy-milk_18.jpg
data/soy-milk/soy-milk_19.jpg
data/soy-milk/soy-milk_20.jpg
data/soy-milk/soy-milk_21.jpg
data/soy-milk/soy-milk_22.jpg
data/soy-milk/soy-milk_23.jpg
data/soy-milk/soy-milk_24.jpg
data/soy-milk/soy-milk_25.jpg
data/soy-milk/soy-milk_26.jpg
data/soy-milk/soy-milk_27.jpg
data/soy-milk/soy-milk_28.jpg
data/soy-milk/soy-milk_29.jpg
data/soy-milk/soy-milk_30.jpg
data/soy-milk/soy-milk_31.jpg
data/soy-milk/soy-milk_32.jpg
data/soy-milk/soy-milk_33.jpg
data/soy-milk/soy-milk_34.jpg
data/soy-milk/soy-milk_35.jpg
data/soy-milk/soy-milk_36.jpg
data/soy-milk/soy-milk_37.jpg

yolov3-tiny-soy-milk.cfg

[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=64
subdivisions=8

width=416
height=416
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 = 500200
policy=steps
steps=400000,450000
scales=.1,.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

[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 = 3,4,5
anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
classes=1
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

[route]
layers = -4

[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=256
size=3
stride=1
pad=1
activation=leaky

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

[yolo]
mask = 1,2,3
anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
classes=1
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1