ATOM_resnet50在OTB100数据集测试结果

最新推荐文章于 2022-04-03 16:57:13 发布
最新推荐文章于 2022-04-03 16:57:13 发布
阅读量961 收藏
点赞数
分类专栏： 笔记 # 目标跟踪 # pytorch 文章标签： pytorch 神经网络 深度学习
zzz
本文链接：https://blog.csdn.net/weixin_45700507/article/details/108173080
版权
笔记 同时被 3 个专栏收录
32 篇文章 0 订阅
订阅专栏
pytorch
25 篇文章 0 订阅
订阅专栏
目标跟踪
20 篇文章 1 订阅
订阅专栏

ATOM resnet50 在OTB100数据集测试结果(tracker_num=1)
结果保存在tracking_results_me_resnet50/result_plots_me_resnet50

Running:  myexperiments  atom_otb
Evaluating    1 trackers on    98 sequences
Tracker: atom default 0 ,  Sequence: Basketball
/home/zhuzhu/anaconda3/envs/pytracking/lib/python3.7/site-packages/torch/nn/functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
  "See the documentation of nn.Upsample for details.".format(mode))
/home/zhuzhu/anaconda3/envs/pytracking/lib/python3.7/site-packages/setuptools/distutils_patch.py:26: UserWarning: Distutils was imported before Setuptools. This usage is discouraged and may exhibit undesirable behaviors or errors. Please use Setuptools' objects directly or at least import Setuptools first.
  "Distutils was imported before Setuptools. This usage is discouraged "
Using /tmp/torch_extensions as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /tmp/torch_extensions/_prroi_pooling/build.ninja...
Building extension module _prroi_pooling...
ninja: no work to do.
Loading extension module _prroi_pooling...
/home/zhuzhu/anaconda3/envs/pytracking/lib/python3.7/site-packages/torch/nn/functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
  "See the documentation of nn.Upsample for details.".format(mode))
FPS: 11.309636145167929
Tracker: atom default 0 ,  Sequence: Biker
FPS: 7.5112431710487275
Tracker: atom default 0 ,  Sequence: Bird1
FPS: 10.546400445487969
Tracker: atom default 0 ,  Sequence: Bird2
FPS: 7.0940343042255085
Tracker: atom default 0 ,  Sequence: BlurBody
FPS: 8.348025896671864
Tracker: atom default 0 ,  Sequence: BlurCar2
FPS: 8.883920139633
Tracker: atom default 0 ,  Sequence: BlurCar3
FPS: 8.8490169482142
Tracker: atom default 0 ,  Sequence: BlurCar4
FPS: 9.4595216397196
Tracker: atom default 0 ,  Sequence: BlurFace
FPS: 7.616327276084982
Tracker: atom default 0 ,  Sequence: BlurOwl
FPS: 7.746352148914754
Tracker: atom default 0 ,  Sequence: Board
FPS: 8.552387494806782
Tracker: atom default 0 ,  Sequence: Bolt
FPS: 8.206512704811415
Tracker: atom default 0 ,  Sequence: Bolt2
FPS: 7.431532618547909
Tracker: atom default 0 ,  Sequence: Box
FPS: 8.758974641417947
Tracker: atom default 0 ,  Sequence: Boy
FPS: 7.944704073712194
Tracker: atom default 0 ,  Sequence: Car1
FPS: 9.441332514564744
Tracker: atom default 0 ,  Sequence: Car2
FPS: 9.088228338320087
Tracker: atom default 0 ,  Sequence: Car24
FPS: 9.710901172221515
Tracker: atom default 0 ,  Sequence: Car4
FPS: 11.417230223241358
Tracker: atom default 0 ,  Sequence: CarDark
FPS: 11.459942681288396
Tracker: atom default 0 ,  Sequence: CarScale
FPS: 10.44646822140225
Tracker: atom default 0 ,  Sequence: ClifBar
FPS: 11.559471961573612
Tracker: atom default 0 ,  Sequence: Coke
FPS: 9.228598107673177
Tracker: atom default 0 ,  Sequence: Couple
FPS: 10.9436323945538
Tracker: atom default 0 ,  Sequence: Coupon
FPS: 10.475927925168032
Tracker: atom default 0 ,  Sequence: Crossing
FPS: 8.650535101348794
Tracker: atom default 0 ,  Sequence: Crowds
FPS: 8.43344080321033
Tracker: atom default 0 ,  Sequence: Dancer
FPS: 10.476854906148771
Tracker: atom default 0 ,  Sequence: Dancer2
FPS: 9.634573234424733
Tracker: atom default 0 ,  Sequence: David
FPS: 12.328305479509998
Tracker: atom default 0 ,  Sequence: David2
FPS: 11.990824192890779
Tracker: atom default 0 ,  Sequence: David3
FPS: 9.23031589093656
Tracker: atom default 0 ,  Sequence: Deer
FPS: 6.730147589488899
Tracker: atom default 0 ,  Sequence: Diving
FPS: 10.614967107652244
Tracker: atom default 0 ,  Sequence: Dog
FPS: 9.80316612186189
Tracker: atom default 0 ,  Sequence: Dog1
FPS: 12.838552981669832
Tracker: atom default 0 ,  Sequence: Doll
FPS: 11.981727501290703
Tracker: atom default 0 ,  Sequence: DragonBaby
FPS: 8.757673893207553
Tracker: atom default 0 ,  Sequence: Dudek
FPS: 11.097037012894608
Tracker: atom default 0 ,  Sequence: FaceOcc1
FPS: 12.278296037091218
Tracker: atom default 0 ,  Sequence: FaceOcc2
FPS: 10.723845448112925
Tracker: atom default 0 ,  Sequence: Fish
FPS: 10.87595540688149
Tracker: atom default 0 ,  Sequence: FleetFace
FPS: 10.736049895666321
Tracker: atom default 0 ,  Sequence: Football
FPS: 10.024058974029636
Tracker: atom default 0 ,  Sequence: Football1
FPS: 10.882701385824314
Tracker: atom default 0 ,  Sequence: Freeman1
FPS: 12.864202708380155
Tracker: atom default 0 ,  Sequence: Freeman3
FPS: 10.224449683011986
Tracker: atom default 0 ,  Sequence: Freeman4
FPS: 10.221323349046315
Tracker: atom default 0 ,  Sequence: Girl
FPS: 12.283939798015707
Tracker: atom default 0 ,  Sequence: Girl2
FPS: 11.757425748356413
Tracker: atom default 0 ,  Sequence: Gym
FPS: 10.991684261533582
Tracker: atom default 0 ,  Sequence: Human2
FPS: 10.00491053983518
Tracker: atom default 0 ,  Sequence: Human3
FPS: 10.724237063803786
Tracker: atom default 0 ,  Sequence: Human4_2
FPS: 9.654040760007318
Tracker: atom default 0 ,  Sequence: Human5
FPS: 10.166361371555565
Tracker: atom default 0 ,  Sequence: Human6
FPS: 9.537229483088797
Tracker: atom default 0 ,  Sequence: Human7
FPS: 9.92986557053947
Tracker: atom default 0 ,  Sequence: Human8
FPS: 13.126613351000087
Tracker: atom default 0 ,  Sequence: Human9
FPS: 9.718303279897972
Tracker: atom default 0 ,  Sequence: Ironman
FPS: 9.399705561933139
Tracker: atom default 0 ,  Sequence: Jogging_1
FPS: 10.522334108135555
Tracker: atom default 0 ,  Sequence: Jogging_2
FPS: 16.422120959914036
Tracker: atom default 0 ,  Sequence: Jump
FPS: 10.895539220666032
Tracker: atom default 0 ,  Sequence: Jumping
FPS: 11.45971715015223
Tracker: atom default 0 ,  Sequence: Lemming
FPS: 11.887408924098672
Tracker: atom default 0 ,  Sequence: Liquor
FPS: 11.39988794135658
Tracker: atom default 0 ,  Sequence: Man
FPS: 10.70190595532231
Tracker: atom default 0 ,  Sequence: Matrix
FPS: 8.15928112333447
Tracker: atom default 0 ,  Sequence: Mhyang
FPS: 12.571104611086495
Tracker: atom default 0 ,  Sequence: MotorRolling
FPS: 9.171376849327812
Tracker: atom default 0 ,  Sequence: MountainBike
FPS: 9.25448228471651
Tracker: atom default 0 ,  Sequence: Panda
FPS: 12.33736881263035
Tracker: atom default 0 ,  Sequence: RedTeam
FPS: 10.043510145898695
Tracker: atom default 0 ,  Sequence: Rubik
FPS: 14.49981102956294
Tracker: atom default 0 ,  Sequence: Shaking
FPS: 15.741543861033097
Tracker: atom default 0 ,  Sequence: Singer1
FPS: 15.574902895731915
Tracker: atom default 0 ,  Sequence: Singer2
FPS: 14.354727955362561
Tracker: atom default 0 ,  Sequence: Skater
FPS: 14.732715456219285
Tracker: atom default 0 ,  Sequence: Skater2
FPS: 17.36507645208887
Tracker: atom default 0 ,  Sequence: Skating1
FPS: 15.712371459691797
Tracker: atom default 0 ,  Sequence: Skating2_1
FPS: 16.602651301522215
Tracker: atom default 0 ,  Sequence: Skating2_2
FPS: 19.357146277699645
Tracker: atom default 0 ,  Sequence: Skiing
FPS: 12.490032877367225
Tracker: atom default 0 ,  Sequence: Soccer
FPS: 16.755266771501443
Tracker: atom default 0 ,  Sequence: Subway
FPS: 15.767329535342476
Tracker: atom default 0 ,  Sequence: Surfer
FPS: 16.379603222780187
Tracker: atom default 0 ,  Sequence: Suv
FPS: 18.551223964740696
Tracker: atom default 0 ,  Sequence: Sylvester
FPS: 15.444170676924973
Tracker: atom default 0 ,  Sequence: Tiger1
FPS: 12.401133029585743
Tracker: atom default 0 ,  Sequence: Tiger2
FPS: 12.37976300594806
Tracker: atom default 0 ,  Sequence: Toy
FPS: 12.503509867806088
Tracker: atom default 0 ,  Sequence: Trans
FPS: 11.439442823537693
Tracker: atom default 0 ,  Sequence: Trellis
FPS: 13.551647598865245
Tracker: atom default 0 ,  Sequence: Twinnings
FPS: 13.384670040928917
Tracker: atom default 0 ,  Sequence: Vase
FPS: 11.86487333294586
Tracker: atom default 0 ,  Sequence: Walking
FPS: 12.675671642091023
Tracker: atom default 0 ,  Sequence: Walking2
FPS: 11.135766080265318
Tracker: atom default 0 ,  Sequence: Woman
FPS: 8.107518644617393
Done
程序共运行：9422.000000秒

在这里插入图片描述在这里插入图片描述

在这里插入图片描述
在这里插入图片描述

朱朱呀
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
专栏目录
OTB数据集结果
05-02
OTB数据集的结果
detection_Resnet50_Final.pth, Resnet50_Final.pth
03-16
detection_Resnet50_Final.pth, Resnet50_Final.pth, md5: bce939bc22d8cec91229716dd932e
ATOM_resnet18_otb100数据集 用自己训练的模型进行测试
weixin_45700507的博客
08-20 1274
run_experiment.py debug=0 atom default atom_otb 结果保存在pytracking.tracking_results_me.atom.default_000 Running: myexperiments atom_otb Evaluating 1 trackers on 98 sequences Tracker: atom default 0 , Sequence: Basketball /home/zhuzhu/anaconda3/envs.
ATOM resnet50/PrDiMP18 在OTB100数据集测试结果
weixin_45700507的博客
08-23 695
ATOM resnet50/PrDiMP18 在OTB100数据集测试结果(tracker_num=1) 结果保存在tracking_results_me_prdimp18_epoch90_atom5/result_plots_me_prdimp18_epoch90_atom50 Running: myexperiments atom_dimp_otb Evaluating 2 trackers on 98 sequences Tracker: dimp prdimp18 0 , ..
UDT算法在数据集OTB评估过程
论文学习笔记-《Fast Online Object Tracking and Segmentation- A Unifying Approach》
04-16 1186
OTB使用：https://www.cnblogs.com/eraserNut/p/8401320.html
ATOM_resnet50在UAV123数据集测试结果
weixin_45700507的博客
08-22 790
ATOM resnet50 在OTB100数据集测试结果(tracker_num=3) 结果保存在tracking_results_me_resnet50/result_plots_me_resnet50 Running: myexperiments atom_uav Evaluating 3 trackers on 123 sequences Tracker: atom default 0 , Sequence: uav_bike1 /home/zhuzhu/anaconda3/env.
ATOM resnet18/PrDiMP18在UAV123/OTB100数据集测试结果
weixin_45700507的博客
08-23 625
ATOM resnet18/PrDiMP18(epoch=90) 在UAV123数据集测试结果(tracker_num=1) 结果保存在tracking_results_me_prdimp18_epoch90_atom18/result_plots_me_prdimp18_epoch90_atom18 Running: myexperiments atom_dimp_uav Evaluating 2 trackers on 123 sequences Tracker: dimp prdim.
ATOM_resnet18_uav数据集 用自己训练的模型进行测试
weixin_45700507的博客
08-18 830
run_experiment.py debug=0 atom default 结果保存在pytracking.tracking_results_me.atom.default_000 Running: myexperiments uav_test Evaluating 1 trackers on 123 sequences Tracker: atom default 0 , Sequence: uav_bike1 /home/zhuzhu/anaconda3/envs/pytrackin.
跟踪基准OTB100、UAV123跟踪结果文件TXT
du的博客
04-03 3314
重要！我提供的所有txt文件都是用pysot-toolkit测试的。 有小伙伴需要txt文件，最近一段时间正好搜集了一部分，也有一些自己测试的。我自己测试的跟踪结果都是用的Tesla P100 GPU。 链接：百度网盘（提取码：sr4y）、GoogleDrive 1.跟踪结果文件来源 (1) OTB100跟踪结果来源 自测结果是在硬件配置GPU Tesla P100环境下完成的，代码、模型、超参数均使用原作者已公布的。 原始结果是算法原作者本人在Github上公开的。 网络资源不确定是什么设备是否为官方代
resnet50.zip_markwyh_resnet50_图像分类_图像数据集_迁移学习
07-15
改变文件位置，可以直接拿来做图像分类，具有易读易懂性
yolact_edge_resnet50_54_800000.pth
09-22
yolact_edge_resnet50_54_800000.pth
ResNet50_ResNet_resnet50_pythonresnet50_
10-01
Resnet50卷积神经网络训练模型，python语言编程，粗略训练，入门难度。
se_resnet50-ce0d4300.pth
08-14
常用torch预训练权重，解决国内下载慢。包括resnet50,resnet101, se_resnet101,se_resnet50等
pytorch之tensor操作报错汇总
weixin_45700507的博客
12-22 2827
torch.split() t = torch.ones((2,5)) list_of_tensors = torch.split(t,[2,1,1],dim=1) print("t:{}".format(t)) for idx,t in enumerate(list_of_tensors): print("di {} ge tensor:{},shape is {}".format(idx+1,t,t.shape)) RuntimeError: s.
PrDiMP_resnet50(修改学习率)训练记录
weixin_45700507的博客
08-29 2279
run_training.py dimp prdimp50 batchsize由10改成6 不然运行不起来 但是只减小batchsize训练的效果不好，loss不是最优的，故同时减小学习率，如下所示。 结果保存在result_model_prdimp_delr 原始学习率 optimizer = optim.Adam([{'params': actor.net.classifier.parameters(), 'lr': 1e-3}, .
pytracking-ATOM代码--用自己训练的模型进行跟踪
weixin_45700507的博客
08-18 1901
把ltr.result_model.checkpoints.ltr.bbreg.atom下的文件ATOMnet_ep0050pth.tar移动到pytracking.networks下，并改名去掉.tar后缀(即解压); 到pytracking.parameter.atom.default.py文件的最后，改写deep_feat那句，把net_path改成刚刚移动的那个文件 deep_feat = deep.ATOMResNet18(net_path='atom_default.pth', ..
keras版本maskrcnn提示str object has no attribute decode
weixin_45700507的博客
03-16 809
报错 original_keras_version = f.attrs['keras_version'].decode('utf8') AttributeError: 'str' object has no attribute 'decode' 解决 卸载原来的h5py模块，安装2.10版本 pip install h5py==2.10 -i https://pypi.tuna.tsinghua.edu.cn/simple/ 参考：https://blog.csdn.net/xiqi4145/a
Track R-CNN代码运行结果
weixin_45700507的博客
09-26 800
(trackrcnn_author) zhuzhu@zhuzhu:/media/zhuzhu/23227915-deb6-45d3-8d7d-7070283de100/zhuzhu/MOTS/TrackR-CNN/TrackR-CNN-master$ python3 main.py configs/conv3d_sep2 "{\"build_networks\":false,\"import_detections\":true,\"task\":\"forward_tracking\",\"dataset\
faster_rcnn_resnet50_fpn faster_rcnn_resnet50_fpn 要怎么使用
最新发布
06-05
在 PyTorch 中使用 `faster_rcnn_resnet50_fpn` 模型，可以按照以下步骤进行： 1. 安装 PyTorch 和 TorchVision 库（如果未安装的话）。 2. 导入必要的库和模块： ```python import torch import torchvision ...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值