Learning Spatiotemporal Features with 3D Convolutional Networks (C3D User Guide) 实验过程
2017-10-27 15:14
465 查看
1.运行 sh c3d_sport1m_feature_extraction_video.sh
出错: syncedmem.cpp:47] Check failed: error == cudaSuccess (30 vs. 0) unknown error
* Check failure stack trace: *
Aborted (core dumped)
解决方法:+ sudo
sudo sh c3d_sport1m_feature_extraction_video.sh
2.接着error: Check failed: error == cudaSuccess (8 vs. 0) invalid device function
* Check failure stack trace: *
Aborted (core dumped)
原因:显卡算力设置有误
解决方法:
https://developer.nvidia.com/cuda-gpus查询自己显卡算力 我使用的是1080Ti 算力是6.1
![](https://oscdn.geek-share.com/Uploads/Images/Content/201710/27/27feadd59614846a38d853aa2a2b4eb8)
打开Makefile.config
![](https://oscdn.geek-share.com/Uploads/Images/Content/201710/27/f37e54f33a3fd7a593231306e51d2b8b)
将最后一行注释删除
提取帧 (也可以直接使用.avi文件)
修改train_01.lst和test_01.lst,使路径指向包含提取帧的目录。
the example uses the first public train/test splits provided by UCF101.
sh ucf101_testing.sh
测试结果是剪辑精度,可以进一步汇总计算出视频级精度.
出错: syncedmem.cpp:47] Check failed: error == cudaSuccess (30 vs. 0) unknown error
* Check failure stack trace: *
Aborted (core dumped)
解决方法:+ sudo
sudo sh c3d_sport1m_feature_extraction_video.sh
2.接着error: Check failed: error == cudaSuccess (8 vs. 0) invalid device function
* Check failure stack trace: *
Aborted (core dumped)
原因:显卡算力设置有误
解决方法:
https://developer.nvidia.com/cuda-gpus查询自己显卡算力 我使用的是1080Ti 算力是6.1
打开Makefile.config
将最后一行注释删除
2.Finetuning C3D Pre-trained model on UCF101
Prepare data
下载 ucf101提取帧 (也可以直接使用.avi文件)
修改train_01.lst和test_01.lst,使路径指向包含提取帧的目录。
the example uses the first public train/test splits provided by UCF101.
开始 finetuning
run:sh ucf101_finetuning.sh
测试 finetuned model
run:sh ucf101_testing.sh
测试结果是剪辑精度,可以进一步汇总计算出视频级精度.
相关文章推荐
- Learning Spatiotemporal Features with 3D Convolutional Networks (C3D User Guide)
- 论文笔记C3D:Learning Spatiotemporal Features with 3D Convolutional Networks
- 时空特征--Learning Spatiotemporal Features with 3D Convolutional Networks
- 【深度学习论文翻译】Learning Spatiotemporal Features with 3D Convolutional Networks全文对照翻译
- [深度学习论文笔记][Video Classification] Learning Spatiotemporal Features with 3D Convolutional Networks
- Learning Spatiotemporal Features with 3D Convolutional Networks译
- 深度学习文章阅读4--Learning Spatiotemporal Features with 3D Convolutional Networks
- 论文阅读笔记《leaning spatiotemporal features with 3D convolutional network》
- Reading papers_16(Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis)
- Learning hierarchical spatio-temporal features for action recognition with ISA
- Reading papers_16(Learning hierarchical invariant spatio-temporal features for action recognition wi
- 论文笔记:Evaluation of local spatio-temporal features for action recognition
- Kibana User Guide [4.2] » Getting Started with Kibana » Defining Your Index Patterns
- STC Fast Tracking via Spatio-Temporal Context Learning 论文笔记
- A 2017 Guide to Semantic Segmentation with Deep Learning 笔记
- 翻译“Learning Transferable Features with Deep Adaptation Networks”
- XMLmind XML Editor - User's Guide(Being productive with XXE:XMLmind使用技巧)
- Correlation Filter in Visual Tracking系列二:Fast Visual Tracking via Dense Spatio-Temporal Context Learning 论文笔记
- A Programmer's Guide to Data Mining 2:Get started with recommendation system(User based filtering)
- 阅读笔记1:fast tracking via spatio-temporal context learning