我目前正在使用来自 AlexeyAB Github 的 yolov4 darknet 训练数据集: https ://github.com/AlexeyAB/darknet
我正在训练的数据集称为 FishNet Open Images。该数据集有 86,029 张图像,每张图像中有 5 个边界框。它有34个班级。目前,我进行了 1561 次迭代,训练很快从现在的 2000 左右的平均误差损失下降到 0.000 相当快。这应该是正常的吗?我觉得我做错了什么!我使用大约 85% 的图像作为训练集,另外 15% 作为验证集。
我的 train.txt 和 test.txt 文件正确,我的 obj.data 正确。我将注释更改为 yolo 格式并配置了 .cfg 文件,如下所示
[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=64
subdivisions=64
width=448
height=448
channels=3
momentum=0.949
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
learning_rate=0.001
burn_in=1000
max_batches = 88000
policy=steps
steps=68800,77400
scales=.1,.1
#cutmix=1
mosaic=1
#:104x104 54:52x52 85:26x26 104:13x13 for 416
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=mish
# Downsample
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[route]
layers = -2
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[route]
layers = -1,-7
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
# Downsample
[convolutional]
batch_normalize=1
filters=128
size=3
stride=2
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[route]
layers = -2
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish
[route]
layers = -1,-10
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
# Downsample
[convolutional]
batch_normalize=1
filters=256
size=3
stride=2
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[route]
layers = -2
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=mish
[route]
layers = -1,-28
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
# Downsample
[convolutional]
batch_normalize=1
filters=512
size=3
stride=2
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[route]
layers = -2
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=mish
[route]
layers = -1,-28
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
# Downsample
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=2
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
[route]
layers = -2
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=mish
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=mish
[route]
layers = -1,-16
[convolutional]
batch_normalize=1
filters=1024
size=1
stride=1
pad=1
activation=mish
stopbackward=800
##########################
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
### SPP ###
[maxpool]
stride=1
size=5
[route]
layers=-2
[maxpool]
stride=1
size=9
[route]
layers=-4
[maxpool]
stride=1
size=13
[route]
layers=-1,-3,-5,-6
### End SPP ###
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = 85
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -1, -3
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = 54
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -1, -3
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
##########################
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=117
activation=linear
[yolo]
mask = 0,1,2
anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
classes=34
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
scale_x_y = 1.2
iou_thresh=0.213
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
nms_kind=greedynms
beta_nms=0.6
max_delta=5
[route]
layers = -4
[convolutional]
batch_normalize=1
size=3
stride=2
pad=1
filters=256
activation=leaky
[route]
layers = -1, -16
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=117
activation=linear
[yolo]
mask = 3,4,5
anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
classes=34
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
scale_x_y = 1.1
iou_thresh=0.213
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
nms_kind=greedynms
beta_nms=0.6
max_delta=5
[route]
layers = -4
[convolutional]
batch_normalize=1
size=3
stride=2
pad=1
filters=512
activation=leaky
[route]
layers = -1, -37
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=117
activation=linear
[yolo]
mask = 6,7,8
anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
classes=34
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
scale_x_y = 1.05
iou_thresh=0.213
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
nms_kind=greedynms
beta_nms=0.6
max_delta=5
这是我的 obj.data
classes = 34
train = data/train.txt
valid = data/valid.txt
names = data/obj.names
backup = backup/