darkflow训练VOC

基于darkflow：https://github.com/thtrieu/darkflow

但是按照原文步骤训练VOC数据集似乎有点问题

AssertionError: labels.txt and cfg/yolo-new.cfg indicate inconsistent class numbers

1）下载VOC数据集

# Download the Pascal VOC dataset:

curl -O https://pjreddie.com/media/files/VOCtest_06-Nov-2007.tar

tar xf VOCtest_06-Nov-2007.tar

# An example of the Pascal VOC annotation format:

vim VOCdevkit/VOC2007/Annotations/000001.xml

2）复制yolo.cfg，重命名为yolotest1.cfg

3）打开yolotest1.cfg，修改 [region] layer (the last layer) to the number of classes you are going to train for. In our case, classes are set to 20:

...

[region]

anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52

bias_match=1

classes=20###！！！

coords=4

num=5

softmax=1

...

4）仍然在yolotest1.cfg中，change filters in the [convolutional] layer (the second to last layer（倒数第二层？）) to num * (classes + 5). In our case, num is 5 and classes are 3 so 5 * (3 + 5) = 40 therefore filters are set to 40.

对于VOC是5*（20+5）=125

...

[convolutional]

size=1

stride=1

pad=1

filters=125

activation=linear

[region]

anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52

...

5）修改labels.txt ，列出20类（VOC）标签
person
bird
cat
cow
dog
horse
sheep
aeroplane
bicycle
boat
bus
car
motorbike
train
bottle
chair
dining table
potted plant
sofa

tv/monitor

6）运行flow --model cfg/yolotest1.cfg --train --dataset "/Users/sisyphus/darkflow/VOCdevkit/VOC2007/JPEGImages" --annotation "/Users/sisyphus/darkflow/VOCdevkit/VOC2007/Annotations"

（注意需要绝对路径！）

运行一步后报错killed9，可能是内存不够。下来在GPU电脑上试试看。