问题描述
我正在用 1 个班级训练 Darknet Yolo(有 9000 个训练示例!),但我有这个输出样本:
v3 (IoU loss,normalizer: (IoU: 0.07,obj: 1.00,cls: 1.00) Region 150 Avg (IoU: 0.000000),count: 1,class_loss = 0.003734,IoU_loss = 0.000000,total_loss = 0.003734
IoU 保持恒定为 0.07,并且类别损失非常低。
(next mAP calculation at 1000 iterations)
250: 0.004589,0.011130 avg loss,0.000004 rate,7.071465 seconds,16000 images,2.931760 hours left
导致这个恒定小IoU的问题是什么?
详情
batch=64
subdivisions=16
width=512
height=512
channels=1
momentum=0.949
decay=0.0005
max_batches = 2000
steps=1600,1800
...
filters=18
activation=linear
[yolo]
mask = 6,7,8
anchors = 12,16,19,36,40,28,75,76,55,72,146,142,110,192,243,459,401
classes=1
obj.data 文件:
classes = 1
train = /content/darknet/build/darknet/x64/data/train.txt
names = /content/darknet/build/darknet/x64/data/obj.names
backup = /content/darknet/build/darknet/x64/backup/
obj.name 文件:
Object
解决方法
首先你需要改变cfg文件。如果你有