资源分类
》 资源 》算法》P3D

P3D

2019-09-19 | |  59 |   0 |   0

Pseudo-3D Residual Networks

This repo implements the network structure of P3D[1] with MXNet, pre-trained model weights are converted from caffemodel, which is supported from the author's repo

Pretrained weights

  1. P3D ResNet trained on Sports-1M dataset: BaiduYun url

  2. P3D ResNet trained on Kinetics dataset: Frame

Reference

[1] [Learning Spatio-Temporal Representation with Pseudo-3D Residual,ICCV2017](http://openaccess.thecvf.com/content_iccv_2017/html/Qiu_Learning_Spatio-Temporal_Representation_ICCV_2017_paper.html)


上一篇：siamese

下一篇：mx-pointnet

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...