资源分类
》 资源 》算法》deformable-3d-convnets

deformable-3d-convnets

2020-04-01 | |  33 |   0 |   0

Deformable-3D-ConvNets

Modified according to resnet2d

##Prerequisite Pytorch 0.2.0
Cuda 8.0
TensorboardX
PIL
setproctitle tqdm colorama pandas numpy

The pretrained models are from https://github.com/kenshohara/3D-ResNets/releases/tag/1.0

First, you need to compile the deformable convolution operation in model/deform3d dir, change the path in make.sh to your own path, then execute bash make.sh.

For Ego-Gesture, you need to modify the data_root, for jester and something-something, you need to additionally provide csv root.


上一篇：modulated-deform-conv

下一篇：Deformable_Convolution_Tensorflow

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...