Skip to content
/ C3D Public

[ICCV 2015] Learning Spatiotemporal Features with 3D Convolutional Networks

License

Notifications You must be signed in to change notification settings

ZJCV/C3D

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

语言: 🇨🇳 🇺🇸

«C3D» 复现了论文Learning Spatiotemporal Features with 3D Convolutional Networks 提出的视频分类模型

C3D扩展了卷积核的维度,通过加入时间维度,将卷积核从空间感受野(HxW)扩展到时空感受野(TxHxW),能够有效的捕捉视频片段中的动作信息

内容列表

使用

训练命令如下:

$ export CUDA_VISIBLE_DEVICES=1
$ export PYTHONPATH=.
$ python tools/train.py --config_file configs/c3d_hmdb51.yaml

本工程使用了PyTorch实现的HMDB51UCF101数据集类,其解析和加载速度非常慢

主要维护人员

  • zhujian - Initial work - zjykzj

参与贡献方式

欢迎任何人的参与!打开issue或提交合并请求。

注意:

许可证

Apache License 2.0 © 2020 zjykzj

About

[ICCV 2015] Learning Spatiotemporal Features with 3D Convolutional Networks

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages