框架简述
Yolov4是一种目标检测算法，具有较高的准确性和速度。Yolov4主要由Darknet-53和Yolov3的改进组成。Darknet-53是一个53层的卷积神经网络，用于提取图像特征。接下来，通过添加FPN和PANet模块来构建特征金字塔网络。然后，通过使用YOLOv3的多尺度预测（多尺度检测特征融合）和特征级联来改进网络性能。
Yolov4引入了一种基于CSPDarknet53的新骨架，名为CSPDarknet53-tiny。该骨架采用了CSP（Cross Stage Partial）连接，通过将主干网络的输出分成两段，一段做卷积处理，另一段保留原始特征，并将两者进行连接。这种结构可以显著减少计算量和参数数量，提高检测性能。
此外，Yolov4还使用了类似EfficientDet的BiFPN（Bi-directional Feature Pyramid Network）模块来实现特征金字塔网络，并在最后几层添加了SAM（Spatial Attention Module）和PAN（Path Aggregation Network）模块来增强网络的感受野和特征表达能力。它是Yolov3的改进版本。
网络对比
网络结构：Yolov4使用了一个更庞大的网络结构，包含更多的卷积层和残差连接，并引入了一些新的模块，如CSPDarknet53、SPP和PANet，以增强特征提取和感知能力。
骨干网络：Yolov4采用了CSPDarknet53作为骨干网络，相比Yolov3的Darknet53，CSPDarknet53拥有更高的准确性和计算效率。
特征金字塔网络（FPN）：Yolov4在特征金字塔网络中使用了PANet模块，它能够有效地融合不同尺度和分辨率的特征图，提升了目标检测的性能。
数据增强策略：Yolov4引入了一些新的数据增强策略，如Mosaic数据增强和CutMix数据增强，以增加模型的泛化能力和鲁棒性。
边界框预测：Yolov4采用了YOLOv3-Tiny中的CIOU损失函数来优化边界框的预测结果，提高了检测的准确度。
参数解读
yolov4关键参数：
[net]
batch=64 # 所有的图片分成all_num/batch个批次，每batch个样本(64)更新一次参数，尽量保证一个batch里面各个类别都能取到样本
subdivisions=64 # 决定每次送入显卡的图片数目 batch/subdivisions
width=608 # 送入网络的图片宽度
height=608 # 送入网络的图片高度
channels=3 # 送入网络的图片通道数
momentum=0.949 # 动量参数，表示梯度下降到最优值的速度
decay=0.0005 # 权重衰减正则项，防止过拟合.
angle=0 # 图片角度变化
saturation = 1.5 # 图片饱和度
exposure = 1.5 # 图片曝光量
hue=.1 # 图片色调
learning_rate=0.0013 # 学习率，影响权值更新的速度
burn_in=1000
max_batches = 500500 # 训练最大次数
policy=steps # 学习率调整的策略
steps=400000,450000 # 学习率调整时间
scales=.1,.1 # 学习率调整倍数
#cutmix=1 # 数据增强cutmix
mosaic=0 # 数据增强mosaic
#:104x104 54:52x52 85:26x26 104:13x13 for 416
[convolutional] # 利用32个大小为3*3*3的滤波器步长为1，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1 # 是否做BN
filters=32 # 输出特征图的数量
size=3 # 卷积核的尺寸
stride=1 # 做卷积运算的步长
pad=1 # 是否做pad
activation=mish # 激活函数类型 # （608 + 2 * 1 - 3）/ 1 + 1 = 608 # 608 * 608 * 32
# Downsample
[convolutional] # 利用64个大小为3*3*3的滤波器步长为2，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=mish # （608 + 2 * 1 - 3）/ 2 + 1 = 304 # 304 * 304 * 64
[convolutional] # 利用64个大小为1*1*3的滤波器步长为1，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish # (304 + 2 * 1 -1) / 1 + 1 = 306 # 304 * 304 * 64
[route]
layers = -2 # 当属性layers只有一个值时，它会输出由该值索引的网络层的特征图 # 304 * 304 * 64
[convolutional] # 利用64个大小为1*1*3的滤波器步长为1，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish # (304 + 2 * 1 -1) / 1 + 1 = 306 # 304 * 304 * 64
[convolutional] # 利用32个大小为1*1*3的滤波器步长为1，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=mish # (304 + 2 * 1 -1) / 1 + 1 = 306 # 304 * 304 * 32
[convolutional] # 利用64个大小为3*3*3的滤波器步长为1，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=mish # (304 + 2 * 1 -3) / 1 + 1 = 304 # 304 * 304 * 64
[shortcut] #shortcut 操作是类似 ResNet 的跨层连接
from=-3 # 参数 from 是 −3，意思是 shortcut 的输出是当前层与先前的倒数第三层相加而得到，通俗来讲就是 add 操作
activation=linear # 304 * 304 * 64
[convolutional] # 利用64个大小为1*1*3的滤波器步长为1，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish # (304 + 2 * 1 -1) / 1 + 1 = 306 # 304 * 304 * 64
[route] # 304 * 304 * 128
layers = -1,-7 # 当属性layers有两个值，就是将上一层和从当前层倒数第7层进行融合，大于两个值同理
[convolutional] # 利用64个大小为1*1*3的滤波器步长为1，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=mish # (304 + 2 * 1 -1) / 1 + 1 = 306 # 304 * 304 * 32
# Downsample
[convolutional] # 利用128个大小为3*3*3的滤波器步长为2，填充值为1进行过滤然后用mish函数进行激活
batch_normalize=1
filters=128
size=3
stride=2
pad=1
activation=mish # (304 + 2 * 1 -3) / 2 + 1 = 152 # 152 * 152 * 32
[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
##########################
[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 ### 每个maxpool的padding=size/2
[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=33
activation=linear
[yolo]
mask = 0,1,2 #对应的anchors索引值
anchors = 23, 40, 25, 79, 44, 77, 30,124, 54,121, 42,197, 87,112, 76,193, 126,255
classes=6
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=33
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
anchors = 23, 40, 25, 79, 44, 77, 30,124, 54,121, 42,197, 87,112, 76,193, 126,255
classes=6
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=33
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
anchors = 23, 40, 25, 79, 44, 77, 30,124, 54,121, 42,197, 87,112, 76,193, 126,255
classes=6
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=0
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
yolov4训练日志：
layer filters size/strd(dil) input output
0 conv 32 3 x 3/ 1 608 x 608 x 3 -> 608 x 608 x 32 0.639 BF
1 conv 64 3 x 3/ 2 608 x 608 x 32 -> 304 x 304 x 64 3.407 BF
2 conv 64 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 64 0.757 BF
3 route 1 -> 304 x 304 x 64
4 conv 64 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 64 0.757 BF
5 conv 32 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 32 0.379 BF
6 conv 64 3 x 3/ 1 304 x 304 x 32 -> 304 x 304 x 64 3.407 BF
7 Shortcut Layer: 4, wt = 0, wn = 0, outputs: 304 x 304 x 64 0.006 BF
8 conv 64 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 64 0.757 BF
9 route 8 2 -> 304 x 304 x 128
10 conv 64 1 x 1/ 1 304 x 304 x 128 -> 304 x 304 x 64 1.514 BF
11 conv 128 3 x 3/ 2 304 x 304 x 64 -> 152 x 152 x 128 3.407 BF
12 conv 64 1 x 1/ 1 152 x 152 x 128 -> 152 x 152 x 64 0.379 BF
13 route 11 -> 152 x 152 x 128
14 conv 64 1 x 1/ 1 152 x 152 x 128 -> 152 x 152 x 64 0.379 BF
15 conv 64 1 x 1/ 1 152 x 152 x 64 -> 152 x 152 x 64 0.189 BF
16 conv 64 3 x 3/ 1 152 x 152 x 64 -> 152 x 152 x 64 1.703 BF
17 Shortcut Layer: 14, wt = 0, wn = 0, outputs: 152 x 152 x 64 0.001 BF
18 conv 64 1 x 1/ 1 152 x 152 x 64 -> 152 x 152 x 64 0.189 BF
19 conv 64 3 x 3/ 1 152 x 152 x 64 -> 152 x 152 x 64 1.703 BF
20 Shortcut Layer: 17, wt = 0, wn = 0, outputs: 152 x 152 x 64 0.001 BF
21 conv 64 1 x 1/ 1 152 x 152 x 64 -> 152 x 152 x 64 0.189 BF
22 route 21 12 -> 152 x 152 x 128
23 conv 128 1 x 1/ 1 152 x 152 x 128 -> 152 x 152 x 128 0.757 BF
24 conv 256 3 x 3/ 2 152 x 152 x 128 -> 76 x 76 x 256 3.407 BF
25 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF
26 route 24 -> 76 x 76 x 256
27 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF
28 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
29 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
30 Shortcut Layer: 27, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
31 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
32 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
33 Shortcut Layer: 30, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
34 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
35 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
36 Shortcut Layer: 33, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
37 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
38 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
39 Shortcut Layer: 36, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
40 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
41 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
42 Shortcut Layer: 39, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
43 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
44 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
45 Shortcut Layer: 42, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
46 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
47 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
48 Shortcut Layer: 45, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
49 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
50 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF
51 Shortcut Layer: 48, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF
52 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF
53 route 52 25 -> 76 x 76 x 256
54 conv 256 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 256 0.757 BF
55 conv 512 3 x 3/ 2 76 x 76 x 256 -> 38 x 38 x 512 3.407 BF
56 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
57 route 55 -> 38 x 38 x 512
58 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
59 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
60 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
61 Shortcut Layer: 58, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
62 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
63 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
64 Shortcut Layer: 61, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
65 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
66 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
67 Shortcut Layer: 64, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
68 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
69 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
70 Shortcut Layer: 67, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
71 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
72 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
73 Shortcut Layer: 70, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
74 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
75 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
76 Shortcut Layer: 73, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
77 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
78 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
79 Shortcut Layer: 76, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
80 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
81 conv 256 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 256 1.703 BF
82 Shortcut Layer: 79, wt = 0, wn = 0, outputs: 38 x 38 x 256 0.000 BF
83 conv 256 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 256 0.189 BF
84 route 83 56 -> 38 x 38 x 512
85 conv 512 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 512 0.757 BF
86 conv 1024 3 x 3/ 2 38 x 38 x 512 -> 19 x 19 x1024 3.407 BF
87 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
88 route 86 -> 19 x 19 x1024
89 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
90 conv 512 1 x 1/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.189 BF
91 conv 512 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x 512 1.703 BF
92 Shortcut Layer: 89, wt = 0, wn = 0, outputs: 19 x 19 x 512 0.000 BF
93 conv 512 1 x 1/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.189 BF
94 conv 512 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x 512 1.703 BF
95 Shortcut Layer: 92, wt = 0, wn = 0, outputs: 19 x 19 x 512 0.000 BF
96 conv 512 1 x 1/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.189 BF
97 conv 512 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x 512 1.703 BF
98 Shortcut Layer: 95, wt = 0, wn = 0, outputs: 19 x 19 x 512 0.000 BF
99 conv 512 1 x 1/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.189 BF
100 conv 512 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x 512 1.703 BF
101 Shortcut Layer: 98, wt = 0, wn = 0, outputs: 19 x 19 x 512 0.000 BF
102 conv 512 1 x 1/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.189 BF
103 route 102 87 -> 19 x 19 x1024
104 conv 1024 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x1024 0.757 BF
105 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
106 conv 1024 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x1024 3.407 BF
107 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
108 max 5x 5/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.005 BF
109 route 107 -> 19 x 19 x 512
110 max 9x 9/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.015 BF
111 route 107 -> 19 x 19 x 512
112 max 13x13/ 1 19 x 19 x 512 -> 19 x 19 x 512 0.031 BF
113 route 112 110 108 107 -> 19 x 19 x2048
114 conv 512 1 x 1/ 1 19 x 19 x2048 -> 19 x 19 x 512 0.757 BF
115 conv 1024 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x1024 3.407 BF
116 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
117 conv 256 1 x 1/ 1 19 x 19 x 512 -> 19 x 19 x 256 0.095 BF
118 upsample 2x 19 x 19 x 256 -> 38 x 38 x 256
119 route 85 -> 38 x 38 x 512
120 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
121 route 120 118 -> 38 x 38 x 512
122 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
123 conv 512 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 512 3.407 BF
124 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
125 conv 512 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 512 3.407 BF
126 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
127 conv 128 1 x 1/ 1 38 x 38 x 256 -> 38 x 38 x 128 0.095 BF
128 upsample 2x 38 x 38 x 128 -> 76 x 76 x 128
129 route 54 -> 76 x 76 x 256
130 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF
131 route 130 128 -> 76 x 76 x 256
132 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF
133 conv 256 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 256 3.407 BF
134 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF
135 conv 256 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 256 3.407 BF
136 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF
137 conv 256 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 256 3.407 BF
138 conv 51 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 51 0.151 BF
139 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.20
140 route 136 -> 76 x 76 x 128
141 conv 256 3 x 3/ 2 76 x 76 x 128 -> 38 x 38 x 256 0.852 BF
142 route 141 126 -> 38 x 38 x 512
143 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
144 conv 512 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 512 3.407 BF
145 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
146 conv 512 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 512 3.407 BF
147 conv 256 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 256 0.379 BF
148 conv 512 3 x 3/ 1 38 x 38 x 256 -> 38 x 38 x 512 3.407 BF
149 conv 51 1 x 1/ 1 38 x 38 x 512 -> 38 x 38 x 51 0.075 BF
150 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.10
151 route 147 -> 38 x 38 x 256
152 conv 512 3 x 3/ 2 38 x 38 x 256 -> 19 x 19 x 512 0.852 BF
153 route 152 116 -> 19 x 19 x1024
154 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
155 conv 1024 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x1024 3.407 BF
156 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
157 conv 1024 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x1024 3.407 BF
158 conv 512 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 512 0.379 BF
159 conv 1024 3 x 3/ 1 19 x 19 x 512 -> 19 x 19 x1024 3.407 BF
160 conv 51 1 x 1/ 1 19 x 19 x1024 -> 19 x 19 x 51 0.038 BF
161 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
Total BFLOPS 127.403
avg_outputs = 1049302
Allocate additional workspace_size = 106.46 MB
以上是yolov4的网络结构，整个网络比较长，因此需要将其各个部分进行归纳总结；YOLOv4网络共有161层，在608 × 608的分辨率下，计算量总共128.46BFLOPS，YOLOv3为141BFLOPS。
