search

koba-jon / pytorch_cpp

Deep Learning sample programs using PyTorch in C++
MIT License
241 stars 52 forks source link
anomaly-detection autoencoder convolutional-autoencoder cpp dagmm dcgan deep-learning dimensionality-reduction generative-modeling image-to-image-translation libtorch linux multiclass-classification object-detection pix2pix pytorch semantic-segmentation u-net vae yolo

readme

PyTorch C++ Samples

[Language]() [LibTorch]()

These are Deep Learning sample programs of PyTorch written in C++.

Description

PyTorch is famous as a kind of Deep Learning Frameworks.
Among them, Python source code is overflowing on the Web, so we can easily write the source code of Deep Learning in Python.
However, there is very little source code written in C++ of compiler language.
Therefore, I hope this repository will help many programmers by providing PyTorch sample programs written in C++.
In addition, I might adapt programs to the latest version.

Updates

06/27,2023: Release of v2.0.1
06/27,2023: Create the heatmap for Anomaly Detection
05/07,2023: Release of v2.0.0
03/01,2023: Release of v1.13.1
09/12,2022: Release of v1.12.1
08/04,2022: Release of v1.12.0
03/18,2022: Release of v1.11.0
02/10,2022: Release of v1.10.2
02/09,2022: Implementation of YOLOv3
01/09,2022: Release of v1.10.1

See more... 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`

Implementation

Details ### Multiclass Classification
Model Paper Conference/Journal Code Release Version
AlexNet A. Krizhevsky et al. NeurIPS 2012 AlexNet v1.7.0
VGGNet K. Simonyan et al. ICLR 2015 VGGNet v1.7.0
ResNet K. He et al. CVPR 2016 ResNet v1.7.0
Discriminator A. Radford et al. ICLR 2016 Discriminator v1.8.1
### Dimensionality Reduction
Model Paper Conference/Journal Code Release Version
Autoencoder G. E. Hinton et al. Science 2006 AE1d v1.8.1
AE2d v1.5.0
Denoising Autoencoder P. Vincent et al. ICML 2008 DAE2d v1.7.0
### Generative Modeling
Model Paper Conference/Journal Code Release Version
Variational Autoencoder D. P. Kingma et al. ICLR 2014 VAE2d v1.5.1
DCGAN A. Radford et al. ICLR 2016 DCGAN v1.5.1
Wasserstein Autoencoder I. Tolstikhin et al. ICLR 2018 WAE2d GAN v1.7.0
WAE2d MMD
### Image-to-Image Translation
Model Paper Conference/Journal Code Release Version
U-Net O. Ronneberger et al. MICCAI 2015 U-Net Regression v1.5.1
pix2pix P. Isola et al. CVPR 2017 pix2pix v1.5.1
### Semantic Segmentation
Model Paper Conference/Journal Code Release Version
SegNet V. Badrinarayanan et al. CVPR 2015 SegNet v1.7.0
U-Net O. Ronneberger et al. MICCAI 2015 U-Net Classification v1.5.1
### Object Detection
Model Paper Conference/Journal Code Release Version
YOLOv1 J. Redmon et al. CVPR 2016 YOLOv1 v1.8.0
YOLOv2 J. Redmon et al. CVPR 2017 YOLOv2 v1.8.0
YOLOv3 J. Redmon et al. arXiv 2018 YOLOv3 v1.10.2
### Anomaly Detection
Model Paper Conference/Journal Code Release Version
AnoGAN T. Schlegl et al. IPMI 2017 AnoGAN2d v1.7.0
DAGMM B. Zong et al. ICLR 2018 DAGMM2d v1.6.0
EGBAD H. Zenati et al. ICLR Workshop 2018 EGBAD2d v1.7.0
GANomaly S. Akçay et al. ACCV 2018 GANomaly2d v1.7.0
Skip-GANomaly S. Akçay et al. IJCNN 2019 Skip-GANomaly2d v1.7.0

Requirement

Details ### 1. PyTorch C++ 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
*** ### 2. OpenCV 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. ### 3. OpenMP This is used to load data in parallel.
(It may be installed on standard Linux OS.) ### 4. Boost This is used for command line arguments, etc.
~~~ $ sudo apt install libboost-dev libboost-all-dev ~~~ ### 5. Gnuplot This is used to display loss graph.
~~~ $ sudo apt install gnuplot ~~~ ### 6. libpng/png++/zlib This is used to load and save index-color image in semantic segmentation.
~~~ $ sudo apt install libpng-dev libpng++-dev zlib1g-dev ~~~

Preparation

Details ### 1. Git Clone ~~~ $ git clone https://github.com/koba-jon/pytorch_cpp.git $ cd pytorch_cpp ~~~ ### 2. Path Setting ~~~ $ 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}) ~~~ ### 3. Compiler Install If you don't have g++ version 8 or above, install it. ~~~ $ sudo apt install g++-8 ~~~ ### 4. Execution Please move to the directory of each model and refer to "README.md".

Utility

Details ### 1. Making Original Dataset 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 ./celebA_org ~~~ You should substitute the path of dataset for "".
Please make sure you have training or test data directly under "". ~~~ $ 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 ../../.. ~~~ ### 2. Data Input System 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 ### 3. Check Progress 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.
![util1](https://user-images.githubusercontent.com/56967584/88464264-3f720300-cef4-11ea-85fd-360cb3a424d1.png)
It corresponds to the following source code in the directory. - progress.cpp - progress.hpp ### 4. Monitoring System 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.
![util2](https://user-images.githubusercontent.com/56967584/88464268-40a33000-cef4-11ea-8a3c-da42d4c803b6.png)
It corresponds to the following source code in the directory. - visualizer.cpp - visualizer.hpp

License

Details You can feel free to use all source code in this repository.
(Click [here](LICENSE) 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

Conclusion

I hope this repository will help many programmers by providing PyTorch sample programs written in C++.
If you have any problems with the source code of this repository, please feel free to "issue".
Let's have a good development and research life!