用yolo区分文字和模糊图像

想不到深度学习如此强大， 为了区分文字和模糊图像，仅用了160张图像，迭代2000次，就可以较好地区分出来了：

绿色框表示模糊，粉红色框表示文字。

如果是用传统方式编程序实现，难度太大了。

不过也有很多分类错的，误识别为模糊的：

观察一下发现蓝天和婴儿误分类为模糊，那就新增2个分类，baby和sky，果然模糊的错误分类减少了：

cfg/yolo-tiny-text-blur.cfg

[net]
batch=64
subdivisions=64
height=448
width=448
channels=3
momentum=0.9
decay=0.0005

learning_rate=0.0001
policy=steps
steps=20,40,60,80,20000,30000
scales=5,5,2,2,.1,.1
max_batches = 40000

[crop]
crop_width=448
crop_height=448
flip=0
angle=0
saturation = 1.5
exposure = 1.5

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

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

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

[connected]
output=256
activation=linear

[connected]
output=4096
activation=leaky

[dropout]
probability=.5

[connected]
output=686
activation=linear

[detection]
classes=4
coords=4
rescore=1
side=7
num=2
softmax=0
sqrt=1
jitter=.2

object_scale=1
noobject_scale=.5
class_scale=1
coord_scale=5