不对的地方求各位纠正
[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=64 一批训练样本的样本数量,每batch个样本更新一次参数
subdivisions=64 batch/subdivisions作为一次性送入训练器的样本数量
如果内存不够大,将batch分割为subdivisions个子batch
上面这两个参数如果电脑内存小,则把batch改小一点,batch越大,训练效果越好
subdivisions越大,可以减轻显卡压力
width=416
height=416
channels=3
以上三个参数为输入图像的参数信息 width和height影响网络对输入图像的分辨率,
从而影响precision,只可以设置成32的倍数
momentum=0.9 DeepLearning1中最优化方法中的动量参数,这个值影响着梯度下降到最优值得速度
decay=0.0005 权重衰减正则项,防止过拟合
angle=0 通过旋转角度来生成更多训练样本
saturation = 1.5 通过调整饱和度来生成更多训练样本
exposure = 1.5 通过调整曝光量来生成更多训练样本
hue=.1 通过调整色调来生成更多训练样本
learning_rate=0.001 学习率决定着权值更新的速度,设置得太大会使结果超过最优值,太小会使下降速度过慢。
如果仅靠人为干预调整参数,需要不断修改学习率。刚开始训练时可以将学习率设置的高一点,
而一定轮数之后,将其减小
在训练过程中,一般根据训练轮数设置动态变化的学习率。
刚开始训练时:学习率以 0.01 ~ 0.001 为宜。
一定轮数过后:逐渐减缓。
接近训练结束:学习速率的衰减应该在100倍以上。
学习率的调整参考https://blog.youkuaiyun.com/qq_33485434/article/details/80452941
burn_in=1000 在迭代次数小于burn_in时,其学习率的更新有一种方式,大于burn_in时,才采用policy的更新方式
max_batches = 500200 训练达到max_batches后停止学习
policy=steps 这个是学习率调整的策略,有policy:constant, steps, exp, poly, step, sig, RANDOM,constant等方式
参考https://nanfei.ink/2018/01/23/YOLOv2%E8%B0%83%E5%8F%82%E6%80%BB%E7%BB%93/#more
steps=40000,45000 下面这两个参数steps和scale是设置学习率的变化,比如迭代到40000次时,学习率衰减十倍。
scales=.1,.1 45000次迭代时,学习率又会在前一个学习率的基础上衰减十倍
[convolutional]
batch_normalize=1 ?
filters=32 输出特征图的数量
size=3 卷积核的尺寸
stride=1 做卷积运算的步长
pad=1 如果pad为0,padding由 padding参数指定。
如果pad为1,padding大小为size/2,padding应该是对输入图像左边缘拓展的像素数量
activation=leaky 激活函数的类型
# Downsample
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=128
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=256
size=3
stride=2
pad=1
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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=512
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters