Question

我正在使用CPU在Windows 10上使用Darknet尝试yolov3-tiny。但是，我一直在平均亏损。我已按照https://github.com/AlexeyAB/darknet.git中的指示按照所有指示进行操作。我用yolo设置为21的所有三个滤镜编辑了cfg文件（因为我只有两个类。）我将细分设置为8，批处理设置为64。我使用的是我自己和我制作的500多幅图像正在尝试进行自定义检测。我希望yolo确定图像是竖起大拇指还是竖起大拇指。我已经运行了多次火车命令，但是我从来没有超过100次迭代

#config file:
[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=64
subdivisions=8
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=2

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

[maxpool]
size=2
stride=1

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

###########

[convolutional]
batch_normalize=1
filters=21
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=21
size=3
stride=1
pad=1
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=21
activation=linear



[yolo]
mask = 3,4,5
anchors = 38, 93,  55,120,  66,156,  90,259, 110,239, 118,283
classes=2
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

[route]
layers = -4

[convolutional]
batch_normalize=1
filters=21
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 8

[convolutional]
batch_normalize=1
filters=21
size=3
stride=1
pad=1
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=21
activation=linear

[yolo]
mask = 0,1,2
anchors = 38, 93,  55,120,  66,156,  90,259, 110,239, 118,283
classes=2
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

Answer 1

尝试：随机= 0

在训练yolov3-tiny时对我有用〜

yolov3-tiny的训练模型，但平均损失始终等于-nan

1 个答案: