ORN
[Home] [Project] [Paper] [Supp] [Poster]
The torch branch contains:
the official torch implementation of ORN.
the MNIST-Variants demo.
Please follow the instruction below to install it and run the experiment demo.
Linux (tested on ubuntu 14.04LTS)
NVIDIA GPU + CUDA CuDNN (CPU mode and CUDA without CuDNN mode are also available but significantly slower)
You can setup everything via a single command wget -O - https://git.io/vHCMI | bash
or do it manually in case something goes wrong:
install the dependencies (required by the demo code):
clone the torch branch:
# git version must be greater than 1.9.10git clone https://github.com/ZhouYanzhao/ORN.git -b torch --single-branch ORN.torchcd ORN.torchexport DIR=$(pwd)
install ORN:
cd $DIR/install# install the CPU/GPU/CuDNN version ORN.bash install.sh
unzip the MNIST dataset:
cd $DIR/demo/datasets unzip MNIST
run the MNIST-Variants demo:
cd $DIR/demo# you can modify the script to test different hyper-parametersbash ./scripts/Train_MNIST.sh
If you run into 'cudnn.find' not found
, update Torch7 to the latest version via cd <TORCH_DIR> && bash ./update.sh
then re-install everything.
CIFAR 10/100
You can train the OR-WideResNet model (converted from WideResNet by simply replacing Conv layers with ORConv layers) on CIFAR dataset with WRN.
dataset=cifar10_original.t7 model=or-wrn widen_factor=4 depth=40 ./scripts/train_cifar.sh
With exactly the same settings, ORN-augmented WideResNet achieves state-of-the-art result while using significantly fewer parameters.
Network | Params | CIFAR-10 (ZCA) | CIFAR-10 (mean/std) | CIFAR-100 (ZCA) | CIFAR-100 (mean/std) -----------------|:--------:|:--------------:|:-------------------:|:---------------:|:--------------------: DenseNet-100-12-dropout | 7.0M | - | 4.10 | - | 20.20 | DenseNet-190-40-dropout | 25.6M | - | 3.46 | - | 17.18 | WRN-40-4 | 8.9M | 4.97 | 4.53 | 22.89 | 21.18 | WRN-28-10-dropout| 36.5M | 4.17 | 3.89 | 20.50 | 18.85 | WRN-40-10-dropout| 55.8M | - | 3.80 | - | 18.3 | ORN-40-4(1/2) | 4.5M | 4.13 | 3.43 | 21.24 | 18.82 | ORN-28-10(1/2)-dropout | 18.2M | 3.52 | 2.98 | 19.22 | 16.15 |
Table.1 Test error (%) on CIFAR10/100 dataset with flip/translation augmentation)
ImageNet
The effectiveness of ORN is further verified on large scale data. The OR-ResNet-18 model upgraded from ResNet-18 yields significant better performance when using similar parameters.
| Network | Params | Top1-Error | Top5-Error | |--------------|:------:|:----------:|:----------:| | ResNet-18 | 11.7M | 30.614 | 10.98 | | OR-ResNet-18 | 11.4M | 28.916 | 9.88 |
Table.2 Validation error (%) on ILSVRC-2012 dataset.
You can use facebook.resnet.torch to train the OR-ResNet-18 model from scratch or finetune it on your data by using the pre-trained weights.
-- To fill the model with the pre-trained weights:model = require('or-resnet.lua')({tensorType='torch.CudaTensor', pretrained='or-resnet18_weights.t7'})
A more specific demo notebook of using the pre-trained OR-ResNet to classify images can be found here.
The pytorch branch contains:
the official pytorch implementation of ORN (alpha version supports 1x1/3x3 ARFs with 4/8 orientation channels only).
the MNIST-Variants demo.
Please follow the instruction below to install it and run the experiment demo.
Linux (tested on ubuntu 14.04LTS)
NVIDIA GPU + CUDA CuDNN (CPU mode and CUDA without CuDNN mode are also available but significantly slower)
install the dependencies (required by the demo code):
clone the pytorch branch:
# git version must be greater than 1.9.10git clone https://github.com/ZhouYanzhao/ORN.git -b pytorch --single-branch ORN.pytorchcd ORN.pytorchexport DIR=$(pwd)
install ORN:
cd $DIR/install bash install.sh
run the MNIST-Variants demo:
cd $DIR/demo# train ORN on MNIST-rotpython main.py --use-arf# train baseline CNNpython main.py
The caffe branch contains:
the official caffe implementation of ORN (alpha version supports 1x1/3x3 ARFs with 4/8 orientation channels only).
the MNIST-Variants demo.
Please follow the instruction below to install it and run the experiment demo.
Linux (tested on ubuntu 14.04LTS)
NVIDIA GPU + CUDA CuDNN (CPU mode and CUDA without CuDNN mode are also available but significantly slower)
install the dependency (required by the demo code):
idx2numpy: pip install idx2numpy
clone the caffe branch:
# git version must be greater than 1.9.10git clone https://github.com/ZhouYanzhao/ORN.git -b caffe --single-branch ORN.caffecd ORN.caffeexport DIR=$(pwd)
install ORN:
# modify Makefile.config first# compile ORN.caffemake clean && make -j"$(nproc)" all
run the MNIST-Variants demo:
cd $DIR/examples/mnist bash get_mnist.sh# train ORN & CNN on MNIST-rotbash train.sh
Due to implementation differences, * upgrading Conv layers to ORConv layers can be done by adding an orn_param
* num_output of ORConv layers should be multipied by nOrientation of ARFs
Example:
layer { type: "Convolution" name: "ORConv" bottom: "Data" top: "ORConv" # add this line to replace regular filters with ARFs orn_param {orientations: 8} param { lr_mult: 1 decay_mult: 2} convolution_param { # this means 10 ARF feature maps num_output: 80 kernel_size: 3 stride: 1 pad: 0 weight_filler { type: "msra"} bias_filler { type: "constant" value: 0} }}
Check the MNIST demo prototxt (and its visualization) for more details.
If you use the code in your research, please cite:
@INPROCEEDINGS{Zhou2017ORN, author = {Zhou, Yanzhao and Ye, Qixiang and Qiu, Qiang and Jiao, Jianbin}, title = {Oriented Response Networks}, booktitle = {CVPR}, year = {2017} }
还没有评论,说两句吧!
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...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com