yolov7 配置文件
时间: 2023-10-20 18:09:18 浏览: 45
YOLOv7是一种目标检测算法,其配置文件包含了模型的各种参数和超参数。下面是一个简单的YOLOv7配置文件示例:
```
[net]
batch=64
subdivisions=16
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
[convolutional]
size=3
stride=1
pad=1
filters=32
activation=leaky
[convolutional]
size=3
stride=2
pad=1
filters=64
activation=leaky
[convolutional]
size=3
stride=1
pad=1
filters=32
activation=leaky
[convolutional]
size=3
stride=2
pad=1
filters=64
activation=leaky
...
[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
...
[route]
layers = -4
[convolutional]
size=3
stride=1
pad=1
filters=128
activation=leaky
...
相关问题: