YOLOV3 config理解 - 知乎

来自 : 知乎 发布时间：2021-03-25

# 动量 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momentum=0.9# 权重衰减正则项，防止过拟合decay=0.0005# 通过旋转角度来生成更多训练样本angle=0# 通过调整饱和度来生成更多训练样本saturation = 1.5# 通过调整曝光量来生成更多训练样本exposure = 1.5# 通过调整色调来生成更多训练样本hue=.1# 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.csdn.net/qq_33485434/article/details/80452941learning_rate=0.001# 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burn_in=1000# 训练达到max_batches后停止学习max_batches = 500200# 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/#morepolicy=steps# 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。# 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steps=400000,450000# 学习率变化的比例，累计相乘scales=.1,.1[convolutional]batch_normalize=1filters=32size=3stride=1pad=1activation=leaky# Downsample[convolutional]batch_normalize=1filters=64size=3stride=2pad=1activation=leaky[convolutional]batch_normalize=1filters=32size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=64size=3stride=1pad=1activation=leaky[shortcut]from=-3activation=linear# Downsample[convolutional]batch_normalize=1filters=128size=3stride=2pad=1activation=leaky[convolutional]batch_normalize=1filters=64size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=128size=3stride=1pad=1activation=leaky[shortcut]from=-3activation=linear[convolutional]batch_normalize=1filters=64size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=128size=3stride=1pad=1activation=leaky[shortcut]from=-3activation=linear# Downsample[convolutional]batch_normalize=1filters=256size=3stride=2pad=1activation=leaky[convolutional]batch_normalize=1filters=128size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=3stride=1pad=1activation=leaky[shortcut]from=-3activation=linear[convolutional]batch_normalize=1filters=128size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=3stride=1pad=1activation=leaky[shortcut]from=-3activation=linear[convolutional]batch_normalize=1filters=128size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=3stride=1pad=1activation=leaky[shortcut]from=-3activation=linear[convolutional]batch_normalize=1filters=128size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=3stride=1pad=1activation=leaky[shortcut]from=-3activation=linear