C3D Introduction
卷积神经网络(CNN)近年被广泛应用于计算机视觉中,包括分类、检测、分割等任务。这些任务一般都是针对图像进行的,使用的是二维卷积(即卷积核的维度为二维)。而基于视频的问题,提特征的方法主要分为双流和C3D两个分支,目前C3D衍生出P3D,I3D等等,这里只介绍最早的C3D caffe版提取特征的步骤以及遇到的问题。
C3D Installation
C3D User Guide
Du Tran (Last modified Mar 20, 2017) C3D-v1.1 is released with new models (Mar 01, 2017). No documentation for v1.1 yet, but some examples for feature extraction, training, and fine-tuning are provided.
文档介绍了C3D 1.0的用法,至于1.1,只有examples。
I.C3D Feature Extration
-
安装好C3D,下载预训练的模型,保存到
YOUR_PATH_TO_C3D/C3D-master/C3D-v1.0/examples/c3d_feature_extraction
-
change dir to
YOUR_PATH_TO_C3D/C3D-master/C3D-v1.0/examples/c3d_feature_extraction
-
Run:
sh c3d_sport1m_feature_extraction_frm.sh or sh c3d_sport1m_feature_extraction_video.sh