[10/22 19:10:39] DALI is not installed, you can improve performance if use DALI
[10/22 19:10:39] [35mDATASET[0m :
[10/22 19:10:39] [35mbatch_size[0m : [92m16[0m
[10/22 19:10:39] [35mnum_workers[0m : [92m4[0m
[10/22 19:10:39] [35mtest[0m :
[10/22 19:10:39] [35mfile_path[0m : [92m/home/aistudio/data/data113093/test_data_joint_motion.npy[0m
[10/22 19:10:39] [35mformat[0m : [92mSkeletonDataset[0m
[10/22 19:10:39] [35mtest_mode[0m : [92mTrue[0m
[10/22 19:10:39] [35mtest_batch_size[0m : [92m1[0m
[10/22 19:10:39] [35mtest_num_workers[0m : [92m0[0m
[10/22 19:10:39] [35mtrain[0m :
[10/22 19:10:39] [35mfile_path[0m : [92m/home/aistudio/data/data113093/train_data_joint_motion.npy[0m
[10/22 19:10:39] [35mformat[0m : [92mSkeletonDataset[0m
[10/22 19:10:39] [35mlabel_path[0m : [92m/home/aistudio/data/data113093/train_label.npy[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mINFERENCE[0m :
[10/22 19:10:39] [35mname[0m : [92mSTGCN_Inference_helper[0m
[10/22 19:10:39] [35mnum_channels[0m : [92m2[0m
[10/22 19:10:39] [35mperson_nums[0m : [92m1[0m
[10/22 19:10:39] [35mvertex_nums[0m : [92m25[0m
[10/22 19:10:39] [35mwindow_size[0m : [92m1500[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mMETRIC[0m :
[10/22 19:10:39] [35mname[0m : [92mSkeletonMetric[0m
[10/22 19:10:39] [35mout_file[0m : [92msubmission.csv[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mMIX[0m :
[10/22 19:10:39] [35malpha[0m : [92m0.5[0m
[10/22 19:10:39] [35mname[0m : [92mMixup[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mMODEL[0m :
[10/22 19:10:39] [35mbackbone[0m :
[10/22 19:10:39] [35mname[0m : [92mAGCN[0m
[10/22 19:10:39] [35mframework[0m : [92mRecognizerGCN[0m
[10/22 19:10:39] [35mhead[0m :
[10/22 19:10:39] [35mls_eps[0m : [92m0.1[0m
[10/22 19:10:39] [35mname[0m : [92mSTGCNHead[0m
[10/22 19:10:39] [35mnum_classes[0m : [92m30[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mOPTIMIZER[0m :
[10/22 19:10:39] [35mlearning_rate[0m :
[10/22 19:10:39] [35mcosine_base_lr[0m : [92m0.05[0m
[10/22 19:10:39] [35miter_step[0m : [92mTrue[0m
[10/22 19:10:39] [35mmax_epoch[0m : [92m100[0m
[10/22 19:10:39] [35mname[0m : [92mCustomWarmupCosineDecay[0m
[10/22 19:10:39] [35mwarmup_epochs[0m : [92m10[0m
[10/22 19:10:39] [35mwarmup_start_lr[0m : [92m0.005[0m
[10/22 19:10:39] [35mmomentum[0m : [92m0.9[0m
[10/22 19:10:39] [35mname[0m : [92mMomentum[0m
[10/22 19:10:39] [35mweight_decay[0m :
[10/22 19:10:39] [35mname[0m : [92mL2[0m
[10/22 19:10:39] [35mvalue[0m : [92m0.0001[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mPIPELINE[0m :
[10/22 19:10:39] [35mtest[0m :
[10/22 19:10:39] [35msample[0m :
[10/22 19:10:39] [35mname[0m : [92mAutoPadding[0m
[10/22 19:10:39] [35mwindow_size[0m : [92m1500[0m
[10/22 19:10:39] [35mtransform[0m :
[10/22 19:10:39] [35mSkeletonNorm[0m : [92mNone[0m
[10/22 19:10:39] [35mtrain[0m :
[10/22 19:10:39] [35msample[0m :
[10/22 19:10:39] [35mname[0m : [92mAutoPadding[0m
[10/22 19:10:39] [35mwindow_size[0m : [92m1500[0m
[10/22 19:10:39] [35mtransform[0m :
[10/22 19:10:39] [35mSkeletonNorm[0m : [92mNone[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mPRECISEBN[0m :
[10/22 19:10:39] [35mnum_iters_preciseBN[0m : [92m200[0m
[10/22 19:10:39] [35mpreciseBN_interval[0m : [92m5[0m
[10/22 19:10:39] ------------------------------------------------------------
[10/22 19:10:39] [35mepochs[0m : [92m100[0m
[10/22 19:10:39] [35mlog_interval[0m : [92m10[0m
[10/22 19:10:39] [35mmodel_name[0m : [92mAGCNJOINT[0m
[10/22 19:10:45] Loading data, it will take some moment...
[10/22 19:10:47] Data Loaded!
[10/22 19:10:50] [35mepoch:[ 1/100][0m [95mtrain step:0 [0m [92mloss: 3.40256 lr: 0.005000 top1: 0.06250 top5: 0.23423[0m [92mbatch_cost: 2.98685 sec,[0m [92mreader_cost: 1.06565 sec,[0m ips: 5.35681 instance/sec.
[10/22 19:11:09] epoch:[ 1/100] [95mtrain step:10 [0m [92mloss: 3.40841 lr: 0.005241 top1: 0.00000 top5: 0.06250[0m [92mbatch_cost: 1.90822 sec,[0m [92mreader_cost: 0.00034 sec,[0m ips: 8.38477 instance/sec.
[10/22 19:11:28] epoch:[ 1/100] [95mtrain step:20 [0m [92mloss: 3.27396 lr: 0.005481 top1: 0.00000 top5: 0.37425[0m [92mbatch_cost: 1.90838 sec,[0m [92mreader_cost: 0.00041 sec,[0m ips: 8.38406 instance/sec.
[10/22 19:11:47] epoch:[ 1/100] [95mtrain step:30 [0m [92mloss: 3.21615 lr: 0.005722 top1: 0.09308 top5: 0.34308[0m [92mbatch_cost: 1.90380 sec,[0m [92mreader_cost: 0.00034 sec,[0m ips: 8.40423 instance/sec.
[10/22 19:12:06] epoch:[ 1/100] [95mtrain step:40 [0m [92mloss: 3.18168 lr: 0.005962 top1: 0.06250 top5: 0.43353[0m [92mbatch_cost: 1.91365 sec,[0m [92mreader_cost: 0.00035 sec,[0m ips: 8.36097 instance/sec.
[10/22 19:12:25] epoch:[ 1/100] [95mtrain step:50 [0m [92mloss: 3.14297 lr: 0.006203 top1: 0.11630 top5: 0.40507[0m [92mbatch_cost: 1.90744 sec,[0m [92mreader_cost: 0.00040 sec,[0m ips: 8.38822 instance/sec.
[10/22 19:12:44] epoch:[ 1/100] [95mtrain step:60 [0m [92mloss: 3.26410 lr: 0.006443 top1: 0.00000 top5: 0.24817[0m [92mbatch_cost: 1.92309 sec,[0m [92mreader_cost: 0.00043 sec,[0m ips: 8.31996 instance/sec.
[10/22 19:13:04] epoch:[ 1/100] [95mtrain step:70 [0m [92mloss: 3.13893 lr: 0.006684 top1: 0.17970 top5: 0.53911[0m [92mbatch_cost: 1.91474 sec,[0m [92mreader_cost: 0.00035 sec,[0m ips: 8.35622 instance/sec.
[10/22 19:13:23] epoch:[ 1/100] [95mtrain step:80 [0m [92mloss: 3.11981 lr: 0.006924 top1: 0.09465 top5: 0.48661[0m [92mbatch_cost: 1.91216 sec,[0m [92mreader_cost: 0.00042 sec,[0m ips: 8.36751 instance/sec.
[10/22 19:13:42] epoch:[ 1/100] [95mtrain step:90 [0m [92mloss: 3.05547 lr: 0.007165 top1: 0.05487 top5: 0.52437[0m [92mbatch_cost: 1.92082 sec,[0m [92mreader_cost: 0.00034 sec,[0m ips: 8.32978 instance/sec.
[10/22 19:14:01] epoch:[ 1/100] [95mtrain step:100 [0m [92mloss: 3.20427 lr: 0.007405 top1: 0.01033 top5: 0.43233[0m [92mbatch_cost: 1.91370 sec,[0m [92mreader_cost: 0.00035 sec,[0m ips: 8.36075 instance/sec.
[10/22 19:14:20] epoch:[ 1/100] [95mtrain step:110 [0m [92mloss: 2.97483 lr: 0.007646 top1: 0.18749 top5: 0.49998[0m [92mbatch_cost: 1.91005 sec,[0m [92mreader_cost: 0.00037 sec,[0m ips: 8.37675 instance/sec.
[10/22 19:14:39] epoch:[ 1/100] [95mtrain step:120 [0m [92mloss: 2.98267 lr: 0.007886 top1: 0.16796 top5: 0.50773[0m [92mbatch_cost: 1.92207 sec,[0m [92mreader_cost: 0.00035 sec,[0m ips: 8.32435 instance/sec.
[10/22 19:14:58] epoch:[ 1/100] [95mtrain step:130 [0m [92mloss: 3.12564 lr: 0.008127 top1: 0.19422 top5: 0.38844[0m [92mbatch_cost: 1.91350 sec,[0m [92mreader_cost: 0.00034 sec,[0m ips: 8.36164 instance/sec.
[10/22 19:15:18] epoch:[ 1/100] [95mtrain step:140 [0m [92mloss: 3.08088 lr: 0.008367 top1: 0.12272 top5: 0.55680[0m [92mbatch_cost: 1.92860 sec,[0m [92mreader_cost: 0.00035 sec,[0m ips: 8.29618 instance/sec.
[10/22 19:15:37] epoch:[ 1/100] [95mtrain step:150 [0m [92mloss: 2.96247 lr: 0.008608 top1: 0.18329 top5: 0.43329[0m [92mbatch_cost: 1.91313 sec,[0m [92mreader_cost: 0.00036 sec,[0m ips: 8.36325 instance/sec.
[10/22 19:15:56] epoch:[ 1/100] [95mtra
没有合适的资源?快使用搜索试试~ 我知道了~
PaddleVideo代码与训练测试数据
共278个文件
py:115个
pyc:101个
yaml:10个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 1 下载量 185 浏览量
2023-01-02
23:19:12
上传
评论
收藏 478.77MB ZIP 举报
温馨提示
PaddleVideo,PaddleVideo代码与训练测试数据 PaddleVideo,PaddleVideo代码与训练测试数据 PaddleVideo,PaddleVideo代码与训练测试数据
资源推荐
资源详情
资源评论
收起资源包目录
PaddleVideo代码与训练测试数据 (278个子文件)
2.2.0 148B
2.2.0 41B
config 279B
submissionB_stgcn_joint_motion.csv 273KB
submissionB_stgcn_bone.csv 273KB
submissionB_stgcn_joint.csv 272KB
submissionB_stgcn_bone_motion.csv 272KB
submissionB_ctrgcn.csv 245KB
submissionB_joint.csv 221KB
submissionB_bone_motion.csv 220KB
submissionB_bone.csv 220KB
submissionB_joint_motion.csv 220KB
description 73B
develop 214B
develop 148B
develop 41B
develop 41B
exclude 240B
FETCH_HEAD 629B
.gitignore 1KB
HEAD 214B
HEAD 214B
HEAD 33B
HEAD 24B
pack-b2ea33e8ff2a9e4755aefe8e30b17115d71a7e59.idx 296KB
pack-244553c50f982707affb402851b51eb67f85cd0b.idx 22KB
MANIFEST.in 205B
index 30KB
LICENSE 11KB
bug_report.md 834B
feature_request.md 595B
custom.md 126B
train_data_joint.npy 2.04GB
testB_data_joint.npy 453.47MB
testA_data_joint.npy 449.18MB
train_label.npy 23KB
pack-b2ea33e8ff2a9e4755aefe8e30b17115d71a7e59.pack 59.59MB
pack-244553c50f982707affb402851b51eb67f85cd0b.pack 397KB
packed-refs 447B
resnet_slowfast.py 28KB
augmentations.py 26KB
refinedstgcn.py 18KB
vit.py 17KB
anet_prop.py 15KB
ctr_gcn.py 14KB
utils.py 14KB
resnet_tweaks_tsm.py 13KB
resnet_tweaks_tsn.py 13KB
paddlevideo_clas.py 13KB
train_multigrid.py 12KB
resnet_tsm.py 12KB
Merger.py 12KB
train.py 12KB
bmn_metric.py 11KB
resnet.py 11KB
bmn.py 10KB
average_precision_calculator.py 10KB
multigrid.py 10KB
decode.py 9KB
save_load_helper.py 9KB
eval_util.py 9KB
dali_loader.py 8KB
sample.py 8KB
custom_lr.py 7KB
bmn_loss.py 6KB
save_load.py 6KB
refinedagcn.py 6KB
short_sampler.py 6KB
attention_lstm_head.py 6KB
anet_pipeline.py 6KB
batchnorm_helper.py 5KB
slowfast_video.py 5KB
config.py 5KB
predict.py 5KB
train_dali.py 5KB
slowfast_head.py 5KB
base.py 5KB
record.py 4KB
export_model.py 4KB
profiler.py 4KB
multi_crop_metric.py 4KB
mean_average_precision_calculator.py 4KB
frame.py 4KB
builder.py 4KB
video.py 4KB
pptsn_head.py 4KB
decode_sampler.py 3KB
skeleton_pipeline.py 3KB
logger.py 3KB
tsm_head.py 3KB
main.py 3KB
precise_bn.py 3KB
pptsm_head.py 3KB
skeleton_metric.py 3KB
weight_init.py 3KB
optimizer.py 3KB
tsn_head.py 3KB
skeleton.py 3KB
base.py 3KB
compose.py 3KB
共 278 条
- 1
- 2
- 3
资源评论
- 幺幺02024-04-04资源内容总结的很到位,内容详实,很受用,学到了~
普通网友
- 粉丝: 1272
- 资源: 5623
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 使用python爬取数据并采用Django搭建系统的前后台,使用Spark进行数据处理并进行电影推荐项目源码
- 基于C++的简易图书管理系统(含exe可执行文件)
- Python毕业设计基于知识图谱的电影推荐系统源码(完整项目代码)
- 国际象棋棋子检测3-YOLO(v5至v9)、COCO、CreateML、Darknet、Paligemma、TFRecord数据集合集.rar
- Hadoop复习资料题库.zip
- 基于python和协同过滤算法的电影推荐系统
- 基于resnet的动物图像分类系统(python期末大作业)PyQt+Flask+HTML5+PyTorch.zip
- 电动蝶阀远程自动化控制系统的构建与应用
- 使用机器学习算法基于用户的社交媒体使用情况预测用户情绪
- jQuery信息提示插件
- 国际象棋棋子检测8-YOLO(v5至v11)、COCO、CreateML、Paligemma、TFRecord、VOC数据集合集.rar
- 2023最新仿蓝奏云合集下载页面系统源码 带后台版本
- Cisco Packet Tracer实用技巧及网络配置指南
- 基于SpringBoot+Vue的家具商城系统设计与实现(编号:97913147)(1).zip
- 基于springboot+vue的大学生创业项目的信息管理系统(编号:96166263).zip
- 基于Springboot的本科实践教学管理系统(编号:1407703).zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功