Skip to content

Latest commit

 

History

History
45 lines (30 loc) · 1.9 KB

README.md

File metadata and controls

45 lines (30 loc) · 1.9 KB
Raw

3D DenseNet in torch

3D DenseNet is using 3D Convolutional(VolumetricConvolution in torch), Pooling, BatchNormalization layers with 3D kernel. This implements is based on DenseNet and fb.resnet.torch. DenseNet introduced in the paper "Densely Connected Convolutional Networks" (CVPR 2017, Best Paper Award)

Requirements

See the installation instructions for a step-by-step guide.

Dataset

  1. Download data through above link;
  2. and modify the file path in train.list and test.list file;
  3. then modify the datadir variable in examples/run_modelnet40.sh.

Training

See the training recipes for addition examples.

For Modelnet40, just run shell examples/run_modelnet40.sh 0,1, 0,1 is the GPU ids with multi-GPU supported.

cd examples
./run_modelnet40_h5.sh 0,1

Trained models

modelnet40_60x validation error rate

Network Top-1 error Top-5 error
Voxnet 13.74 1.92
DenseNet-20-12 12.99 2.03
DenseNet-30-12 12.11 1.94
DenseNet-30-16 11.08 1.61
DenseNet-40-12 11.57 1.78

Notes

This implementation differs from the ResNet paper in a few ways:

3D Convolution: We use the VolumetricConvolution to implement 3D Convolution.