01/09,2022: Fixed execution error in test on CPU package
11/12,2021: Release of v1.10.0
09/27,2021: Release of v1.9.1
09/27,2021: Support for using different devices between training and test
09/06,2021: Improved accuracy of time measurement using GPU
06/19,2021: Release of v1.9.0
03/29,2021: Release of v1.8.1
03/18,2021: Implementation of Discriminator from DCGAN
03/17,2021: Implementation of AE1d
03/16,2021: Release of v1.8.0
03/15,2021: Implementation of YOLOv2
02/11,2021: Implementation of YOLOv1
01/21,2021: Release of v1.7.1
10/30,2020: Release of v1.7.0
10/04,2020: Implementation of Skip-GANomaly2d
10/03,2020: Implementation of GANomaly2d
09/29,2020: Implementation of EGBAD2d
09/28,2020: Implementation of AnoGAN2d
09/27,2020: Implementation of SegNet
09/26,2020: Implementation of DAE2d
09/13,2020: Implementation of ResNet
09/07,2020: Implementation of VGGNet
09/05,2020: Implementation of AlexNet
09/02,2020: Implementation of WAE2d GAN and WAE2d MMD
08/30,2020: Release of v1.6.0
06/26,2020: Implementation of DAGMM2d
06/26,2020: Release of v1.5.1
06/26,2020: Implementation of VAE2d and DCGAN
06/01,2020: Implementation of pix2pix
05/29,2020: Implementation of U-Net Classification
05/26,2020: Implementation of U-Net Regression
04/24,2020: Release of v1.5.0
03/23,2020: Implementation of AE2d

Please select the environment to use as follows on PyTorch official.
PyTorch official : https://pytorch.org/

PyTorch Build : Stable (2.0.1)
Your OS : Linux
Package : LibTorch
Language : C++ / Java
Run this Command : Download here (cxx11 ABI)
CUDA 11.7 : https://download.pytorch.org/libtorch/cu117/libtorch-cxx11-abi-shared-with-deps-2.0.1%2Bcu117.zip
CUDA 11.8 : https://download.pytorch.org/libtorch/cu118/libtorch-cxx11-abi-shared-with-deps-2.0.1%2Bcu118.zip
CPU : https://download.pytorch.org/libtorch/cpu/libtorch-cxx11-abi-shared-with-deps-2.0.1%2Bcpu.zip

version : 3.0.0 or more
This is used for pre-processing and post-processing.
Please refer to other sites for more detailed installation method.

This is used to load data in parallel.
(It may be installed on standard Linux OS.)

This is used for command line arguments, etc.

$ sudo apt install libboost-dev libboost-all-dev

This is used to display loss graph.

$ sudo apt install gnuplot

This is used to load and save index-color image in semantic segmentation.

$ sudo apt install libpng-dev libpng++-dev zlib1g-dev

$ git clone https://github.com/koba-jon/pytorch_cpp.git
$ cd pytorch_cpp

$ vi utils/CMakeLists.txt

Please change the 4th line of "CMakeLists.txt" according to the path of the directory "libtorch".
The following is an example where the directory "libtorch" is located directly under the directory "HOME".

3: # LibTorch
4: set(LIBTORCH_DIR $ENV{HOME}/libtorch)
5: list(APPEND CMAKE_PREFIX_PATH ${LIBTORCH_DIR})

If you don't have g++ version 8 or above, install it.

$ sudo apt install g++-8

Please move to the directory of each model and refer to "README.md".

Please create a link for the original dataset.
The following is an example of "AE2d" using "celebA" Dataset.

$ cd Dimensionality_Reduction/AE2d/datasets
$ ln -s <dataset_path> ./celebA_org

You should substitute the path of dataset for "<dataset_path>".
Please make sure you have training or test data directly under "<dataset_path>".

$ vi ../../../scripts/hold_out.sh

Please edit the file for original dataset.

#!/bin/bash

SCRIPT_DIR=$(cd $(dirname $0); pwd)

python3 ${SCRIPT_DIR}/hold_out.py \
    --input_dir "celebA_org" \
    --output_dir "celebA" \
    --train_rate 9 \
    --valid_rate 1

By running this file, you can split it into training and validation data.

$ sudo apt install python3 python3-pip
$ pip3 install natsort
$ sh ../../../scripts/hold_out.sh
$ cd ../../..

There are transform, dataset and dataloader for data input in this repository.
It corresponds to the following source code in the directory, and we can add new function to the source code below.

• transforms.cpp
• transforms.hpp
• datasets.cpp
• datasets.hpp
• dataloader.cpp
• dataloader.hpp

There are a feature to check progress for training in this repository.
We can watch the number of epoch, loss, time and speed in training.

It corresponds to the following source code in the directory.

• progress.cpp
• progress.hpp

There are monitoring system for training in this repository.
We can watch output image and loss graph.
The feature to watch output image is in the "samples" in the directory "checkpoints" created during training.
The feature to watch loss graph is in the "graph" in the directory "checkpoints" created during training.

It corresponds to the following source code in the directory.

• visualizer.cpp
• visualizer.hpp

You can feel free to use all source code in this repository.
(Click here for details.)

But if you exploit external libraries (e.g. redistribution), you should be careful.
At a minimum, the license notation at the following URL is required.
In addition, third party copyrights belong to their respective owners.

• PyTorch
  Official : https://pytorch.org/
  License : https://github.com/pytorch/pytorch/blob/master/LICENSE
  

• OpenCV
  Official : https://opencv.org/
  License : https://opencv.org/license/
  

• OpenMP
  Official : https://www.openmp.org/
  License : https://gcc.gnu.org/onlinedocs/
  

• Boost
  Official : https://www.boost.org/
  License : https://www.boost.org/users/license.html
  

• Gnuplot
  Official : http://www.gnuplot.info/
  License : https://sourceforge.net/p/gnuplot/gnuplot-main/ci/master/tree/Copyright
  

• libpng/png++/zlib
  Official (libpng) : http://www.libpng.org/pub/png/libpng.html
  License (libpng) : http://www.libpng.org/pub/png/src/libpng-LICENSE.txt
  Official (png++) : https://www.nongnu.org/pngpp/
  License (png++) : https://www.nongnu.org/pngpp/license.html
  Official (zlib) : https://zlib.net/
  License (zlib) : https://zlib.net/zlib_license.html