热门标签
热门文章
- 1openCV环境搭建_impicxxd.lib
- 2Leetcode之string
- 3Android开发基础——真机测试错误,ADB启动不了,程序安装不了,the connection to adb is down,INSTALL_CANCELED_BY_USER..._adb搭建好了,用安装器还是没有adb,启动不了adb,一直让下载,选取,怎么回事
- 4硬盘柱面损坏怎么办_最靠谱的机械硬盘坏道修复工具一：DiskGenius
- 5QtScrcpy：高效便捷的跨平台屏幕录制工具
- 6为什么你要写博客？_写博客的理由
- 7图嵌入 DeepWalk
- 8群晖NAS+路由外网访问配置_群晖 手动路由器设置
- 92023推免夏令营末班车
- 10毕设分享 基于大数据的用户画像分析系统_智能用户画像技术体系
当前位置: article > 正文
【Visdrone数据集】Vsidrone+Yolov5结果记录_visdrone.pt 百度云
作者：正经夜光杯 | 2024-07-20 15:20:55
赞
踩
visdrone.pt 百度云
YOLOV5
yolov5s epoch=100
训练
训练代码：yolov5s 100epoch
- 命令
python train.py --data VisDrone.yaml --weights yolov5s.pt --img 640
- 1
分辨率：img=640
输出权重文件：exp4
验证集
- 运行验证集命令：
python val.py --weights ./runs/train/exp4/weights/best.pt --data VisDrone.yaml --img 640 --task val
- 1
-
验证集结果
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 18/18 [00:16<00:00, 1.11it/s] all 548 38759 0.443 0.34 0.33 0.18 pedestrian 548 8844 0.472 0.379 0.388 0.163 people 548 5125 0.442 0.336 0.322 0.111 bicycle 548 1287 0.251 0.156 0.114 0.0415 car 548 14064 0.63 0.719 0.73 0.488 van 548 1975 0.467 0.354 0.354 0.24 truck 548 750 0.478 0.301 0.314 0.194 tricycle 548 1045 0.432 0.197 0.198 0.101- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
awning-tricycle 548 532 0.26 0.126 0.111 0.0697
bus 548 251 0.533 0.406 0.388 0.238
motor 548 4886 0.466 0.426 0.379 0.149
测试集
- 运行测试集命令：
python val.py --weights ./runs/train/exp4/weights/best.pt --data VisDrone.yaml --img 640 --task val
- 1
- 测试集结果
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 51/51 [00:26<00:00, 1.92it/s]
all 1610 75102 0.394 0.309 0.282 0.15
pedestrian 1610 21006 0.415 0.252 0.245 0.0928
people 1610 6376 0.393 0.172 0.162 0.0511
bicycle 1610 1302 0.231 0.0891 0.0767 0.0277
car 1610 28074 0.587 0.715 0.693 0.412
van 1610 5771 0.35 0.374 0.311 0.19
truck 1610 2659 0.368 0.389 0.317 0.176
tricycle 1610 530 0.229 0.175 0.115 0.0561
awning-tricycle 1610 599 0.364 0.139 0.152 0.0834
bus 1610 2940 0.62 0.505 0.529 0.337
motor 1610 5845 0.379 0.282 0.22 0.0781
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
yolov5s epoch=300
训练
训练代码：yolov5s 300epoch （直接在train.py中改了epoch默认值）
- 命令
python train.py --data VisDrone.yaml --weights yolov5s.pt --img 640
- 1
分辨率：img=640
输出权重文件：exp5
验证集
- 运行验证集命令
python val.py --weights ./runs/train/exp5/weights/best.pt --data VisDrone.yaml --img 640 --task val
- 1
- 验证集结果
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 18/18 [00:16<00:00, 1.12it/s]
all 548 38759 0.466 0.353 0.35 0.194
pedestrian 548 8844 0.48 0.389 0.401 0.17
people 548 5125 0.453 0.348 0.332 0.12
bicycle 548 1287 0.303 0.145 0.129 0.0465
car 548 14064 0.641 0.727 0.74 0.5
van 548 1975 0.464 0.376 0.374 0.255
truck 548 750 0.515 0.317 0.332 0.205
tricycle 548 1045 0.421 0.224 0.214 0.112
awning-tricycle 548 532 0.316 0.145 0.125 0.0795
bus 548 251 0.597 0.426 0.457 0.292
motor 548 4886 0.474 0.437 0.394 0.16
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
测试集
- 运行测试集命令
python val.py --weights ./runs/train/exp5/weights/best.pt --data VisDrone.yaml --img 640 --task test
- 1
-测试集结果
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 51/51 [00:26<00:00, 1.93it/s]
all 1610 75102 0.421 0.314 0.294 0.158
pedestrian 1610 21006 0.43 0.256 0.249 0.095
people 1610 6376 0.424 0.168 0.166 0.055
bicycle 1610 1302 0.255 0.073 0.0811 0.0284
car 1610 28074 0.605 0.718 0.699 0.419
van 1610 5771 0.371 0.365 0.32 0.199
truck 1610 2659 0.4 0.384 0.332 0.189
tricycle 1610 530 0.254 0.209 0.143 0.0664
awning-tricycle 1610 599 0.415 0.174 0.169 0.0897
bus 1610 2940 0.657 0.506 0.546 0.351
motor 1610 5845 0.404 0.285 0.233 0.0849
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
YOLOv5l
yolov5l epoch=300(实际运行了240epoch左右 提前终止了)
训练
- 训练运行命令
python train.py --data VisDrone.yaml --weights yolov5l.pt --img 640 --device 0 --batch-size 8 --cfg models/yolov5l.yaml --device 0,1 --name yolov5l_visdrone
- 1
分辨率：640*640 epoch=300
输出权重文件夹： yolov5l_visdrone
验证集
- 运行验证集命令
python val.py --weights ./runs/train/yolov5l_visdrone/weights/best.pt --data VisDrone.yaml --img 640 --task val
- 1
- 验证集结果
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 18/18 [00:22<00:00, 1.23s/it]
all 548 38759 0.532 0.407 0.417 0.25
pedestrian 548 8844 0.593 0.447 0.49 0.234
people 548 5125 0.521 0.367 0.385 0.153
bicycle 548 1287 0.376 0.204 0.199 0.086
car 548 14064 0.727 0.755 0.788 0.563
van 548 1975 0.527 0.434 0.432 0.312
truck 548 750 0.545 0.369 0.395 0.267
tricycle 548 1045 0.479 0.318 0.299 0.17
awning-tricycle 548 532 0.304 0.173 0.153 0.0955
bus 548 251 0.688 0.514 0.562 0.407
motor 548 4886 0.555 0.488 0.466 0.212
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
测试集
- 测试集运行命令
python val.py --weights ./runs/train/yolov5l_visdrone/weights/best.pt --data VisDrone.yaml --img 640 --task test
- 1
- 测试集结果
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 51/51 [00:47<00:00, 1.08it/s]
all 1610 75102 0.46 0.373 0.345 0.197
pedestrian 1610 21006 0.517 0.302 0.314 0.129
people 1610 6376 0.461 0.201 0.201 0.0711
bicycle 1610 1302 0.297 0.121 0.119 0.0479
car 1610 28074 0.663 0.748 0.744 0.472
van 1610 5771 0.417 0.417 0.371 0.245
truck 1610 2659 0.446 0.454 0.41 0.258
tricycle 1610 530 0.297 0.328 0.211 0.108
awning-tricycle 1610 599 0.367 0.235 0.195 0.111
bus 1610 2940 0.672 0.559 0.588 0.409
motor 1610 5845 0.461 0.361 0.3 0.119
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
yolov5l splite
- 验证集
python val.py --weights /home/sedlight/lxs/yolov5/yolov5-master/runs/train/yolov5l_visdrone_splite12/weights/best.pt --da
ta VisDrone.yaml --img 2560 --task val
- 1
- 2
val: Scanning /home/sedlight/lxs/yolov5/datasets/VisDrone/VisDrone2019-DET-val/labels.cache... 548 images, 0 backgrounds, 0 corrupt: 100%|██████████| 548/548 [00:00<?, ?it/s]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 69/69 [01:41<00:00, 1.47s/it]
all 548 38759 0.7 0.617 0.651 0.429
pedestrian 548 8844 0.748 0.699 0.764 0.432
people 548 5125 0.723 0.608 0.648 0.312
bicycle 548 1287 0.638 0.466 0.513 0.284
car 548 14064 0.837 0.883 0.916 0.707
van 548 1975 0.681 0.62 0.652 0.498
truck 548 750 0.685 0.569 0.614 0.453
tricycle 548 1045 0.631 0.56 0.563 0.364
awning-tricycle 548 532 0.466 0.335 0.33 0.227
bus 548 251 0.847 0.726 0.787 0.611
motor 548 4886 0.74 0.702 0.729 0.403
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 测试集
Evaluation Completed. The peformance of the detector is presented as follows.
Average Precision (AP) @[ IoU=0.50:0.95 | maxDets=500 ] = 32.96%.
Average Precision (AP) @[ IoU=0.50 | maxDets=500 ] = 52.35%.
Average Precision (AP) @[ IoU=0.75 | maxDets=500 ] = 35.21%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets= 1 ] = 0.39%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets= 10 ] = 6.19%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets=100 ] = 38.72%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets=500 ] = 41.24%.
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
yolov5+swim transformer
- 验证集
python val.py --weights /home/sedlight/lxs/yolov5/yolov5-master/runs/train/yolov5l_visdrone_splite_swin18/weights/best.pt --data VisDrone.yaml --img 2560 --task val --device 0,1
- 1
val: Scanning /home/sedlight/lxs/yolov5/datasets/VisDrone/VisDrone2019-DET-val/labels.cache... 548 images, 0 backgrounds, 0 corrupt: 100%|██████████| 548/548 [00:00<?, ?it/s]
Class Images Instances P R mAP50 mAP50-95: 100%|██████████| 69/69 [03:48<00:00, 3.31s/it]
all 548 38759 0.669 0.578 0.612 0.398
pedestrian 548 8844 0.73 0.669 0.733 0.405
people 548 5125 0.708 0.533 0.585 0.276
bicycle 548 1287 0.589 0.447 0.475 0.254
car 548 14064 0.818 0.878 0.909 0.696
van 548 1975 0.64 0.59 0.624 0.477
truck 548 750 0.598 0.556 0.563 0.401
tricycle 548 1045 0.656 0.456 0.507 0.326
awning-tricycle 548 532 0.468 0.283 0.29 0.198
bus 548 251 0.764 0.684 0.733 0.56
motor 548 4886 0.717 0.681 0.707 0.383
Speed: 2.3ms pre-process, 370.9ms inference, 23.0ms NMS per image at shape (8, 3, 2560, 2560)
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 测试集matlab
Evaluation Completed. The peformance of the detector is presented as follows.
Average Precision (AP) @[ IoU=0.50:0.95 | maxDets=500 ] = 30.39%.
Average Precision (AP) @[ IoU=0.50 | maxDets=500 ] = 48.15%.
Average Precision (AP) @[ IoU=0.75 | maxDets=500 ] = 32.51%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets= 1 ] = 0.38%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets= 10 ] = 6.39%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets=100 ] = 36.27%.
Average Recall (AR) @[ IoU=0.50:0.95 | maxDets=500 ] = 38.16%.
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/正经夜光杯/article/detail/857392
推荐阅读
相关标签
