摘要
本文介绍我自研的下采样模块。稍后补充具体的改进方法。大家先看测试结果。
YoloV8官方结果
YOLOv8l summary (fused): 268 layers, 43631280 parameters, 0 gradients, 165.0 GFLOPs
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 29/29 [
all 230 1412 0.922 0.957 0.986 0.737
c17 230 131 0.973 0.992 0.995 0.825
c5 230 68 0.945 1 0.995 0.836
helicopter 230 43 0.96 0.907 0.951 0.607
c130 230 85 0.984 1 0.995 0.655
f16 230 57 0.955 0.965 0.985 0.669
b2 230 2 0.704 1 0.995 0.722
other 230 86 0.903 0.942 0.963 0.534
b52 230 70 0.96 0.971 0.978 0.831
kc10 230 62 0.999 0.984 0.99 0.847
command 230 40 0.97 1 0.995 0.811
f15 230 123 0.891 1 0.992 0.701
kc135 230 91 0.971 0.989 0.986 0.712
a10 230 27 1 0.555 0.899 0.456
b1 230 20 0.972 1 0.995 0.793
aew 230 25 0.945 1 0.99 0.784
f22 230 17 0.913 1 0.995 0.725
p3 230 105 0.99 1 0.995 0.801
p8 230 1 0.637 1 0.995 0.597
f35 230 32 0.939 0.938 0.978 0.574
f18 230 125 0.985 0.992 0.987 0.817
v22 230 41 0.983 1 0.995 0.69
su-27 230 31 0.925 1 0.995 0.859
il-38 230 27 0.972 1 0.995 0.811
tu-134 230 1 0.663 1 0.995 0.895
su-33 230 2 1 0.611 0.995 0.796
an-70 230 2 0.766 1 0.995 0.73
tu-22 230 98 0.984 1 0.995 0.831
Speed: 0.2ms preprocess, 3.8ms inference, 0.0ms loss, 0.8ms postprocess per image
改进后的测试结果
YOLOv8l summary (fused): 286 layers, 42157232 parameters, 0 gradients, 161.8 GFLOPs
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 15/15 [00:03<00:00, 3.93it/s]
all 230 1412 0.965 0.973 0.991 0.751
c17 230 131 0.979 0.985 0.995 0.823
c5 230 68 0.957 0.973 0.993 0.82
helicopter 230 43 0.953 1 0.982 0.628
c130 230 85 0.98 0.988 0.994 0.652
f16 230 57 0.992 0.947 0.989 0.676
b2 230 2 0.911 1 0.995 0.796
other 230 86 0.994 0.953 0.978 0.557
b52 230 70 0.97 0.986 0.987 0.839
kc10 230 62 1 0.981 0.989 0.848
command 230 40 0.992 1 0.995 0.825
f15 230 123 0.958 0.992 0.994 0.708
kc135 230 91 0.997 0.989 0.991 0.715
a10 230 27 1 0.5 0.945 0.507
b1 230 20 0.991 1 0.995 0.728
aew 230 25 0.931 1 0.995 0.791
f22 230 17 0.986 1 0.995 0.778
p3 230 105 1 0.977 0.995 0.794
p8 230 1 0.848 1 0.995 0.796
f35 230 32 0.997 1 0.995 0.575
f18 230 125 0.99 0.992 0.99 0.822
v22 230 41 0.994 1 0.995 0.755
su-27 230 31 0.991 1 0.995 0.858
il-38 230 27 0.99 1 0.995 0.832
tu-134 230 1 0.847 1 0.995 0.895
su-33 230 2 0.916 1 0.995 0.63
an-70 230 2 0.901 1 0.995 0.796
tu-22 230 98 0.998 1 0.995 0.829
Speed: 0.1ms preprocess, 6.2ms inference, 0.0ms loss, 0.4ms postprocess per image