<h1 align="center">
<img src="images/pytorch_cpp.png" width="50%">
</h1>
<p align="center">
C++ Implementation of PyTorch Tutorials for Everyone
<br />
<img src="https://img.shields.io/github/license/prabhuomkar/pytorch-cpp">
<img src="https://img.shields.io/badge/libtorch-2.1.1-ee4c2c">
<img src="https://img.shields.io/badge/cmake-3.14-064f8d">
</p>
| OS (Compiler)\\LibTorch | 2.1.1 |
| :--------------------- | :--------------------------------------------------------------------------------------------------- |
| macOS (clang 11, 12, 13) | [](https://github.com/prabhuomkar/pytorch-cpp/actions?query=workflow%3Aci-build-macos) |
| Linux (gcc 9, 10, 11) | [](https://github.com/prabhuomkar/pytorch-cpp/actions?query=workflow%3Aci-build-ubuntu) |
| Windows (msvc 2019, 2022) | [](https://github.com/prabhuomkar/pytorch-cpp/actions?query=workflow%3Aci-build-windows) |
## Table of Contents
This repository provides tutorial code in C++ for deep learning researchers to learn PyTorch _(i.e. Section 1 to 3)_
**Python Tutorial**: [https://github.com/yunjey/pytorch-tutorial](https://github.com/yunjey/pytorch-tutorial)
### 1. Basics
* [PyTorch Basics](tutorials/basics/pytorch_basics/main.cpp)
* [Linear Regression](tutorials/basics/linear_regression/main.cpp)
* [Logistic Regression](tutorials/basics/logistic_regression/main.cpp)
* [Feedforward Neural Network](tutorials/basics/feedforward_neural_network/src/main.cpp)
### 2. Intermediate
* [Convolutional Neural Network](tutorials/intermediate/convolutional_neural_network/src/main.cpp)
* [Deep Residual Network](tutorials/intermediate/deep_residual_network/src/main.cpp)
* [Recurrent Neural Network](tutorials/intermediate/recurrent_neural_network/src/main.cpp)
* [Bidirectional Recurrent Neural Network](tutorials/intermediate/bidirectional_recurrent_neural_network/src/main.cpp)
* [Language Model (RNN-LM)](tutorials/intermediate/language_model/src/main.cpp)
### 3. Advanced
* [Generative Adversarial Networks](tutorials/advanced/generative_adversarial_network/main.cpp)
* [Variational Auto-Encoder](tutorials/advanced/variational_autoencoder/src/main.cpp)
* [Neural Style Transfer](tutorials/advanced/neural_style_transfer/src/main.cpp)
* [Image Captioning (CNN-AttentionRNN)](tutorials/advanced/image_captioning/src/main.cpp)
### 4. Interactive Tutorials
* [Tensor Slicing](notebooks/tensor_slicing.ipynb)
### 5. Other Popular Tutorials
* [Deep Learning with PyTorch: A 60 Minute Blitz](tutorials/popular/blitz)
# Getting Started
## Requirements
1. [C++-17](http://www.cplusplus.com/doc/tutorial/introduction/) compatible compiler
2. [CMake](https://cmake.org/download/) (minimum version 3.14)
3. [LibTorch version >= 1.12.0 and <= 2.1.1](https://pytorch.org/cppdocs/installing.html)
4. [Conda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/download.html)
## For Interactive Tutorials
**Note**: Interactive Tutorials are currently running on **LibTorch Nightly Version**.
So there are some tutorials which can break when working with _nightly version_.
```bash
conda create --name pytorch-cpp
conda activate pytorch-cpp
conda install xeus-cling notebook -c conda-forge
```
## Clone, build and run tutorials
### In Google Colab
[](https://colab.research.google.com/github/prabhuomkar/pytorch-cpp/blob/master/notebooks/pytorch_cpp_colab_notebook.ipynb)
### On Local Machine
```bash
git clone https://github.com/prabhuomkar/pytorch-cpp.git
cd pytorch-cpp
```
#### Generate build system
```bash
cmake -B build #<options>
```
> **_Note for Windows users:_**<br>
> Libtorch only supports 64bit Windows and an x64 generator needs to be specified. For Visual Studio this can be done by appending `-A x64` to the above command.
Some useful options:
| Option | Default | Description |
| :------------- |:------------|-----:|
| `-D CUDA_V=(11.8\|12.1\|none)` | `none` | Download LibTorch for a CUDA version (`none` = download CPU version). |
| `-D LIBTORCH_DOWNLOAD_BUILD_TYPE=(Release\|Debug)` | `Release` | Determines which libtorch build type version to download (only relevant on **Windows**).|
| `-D DOWNLOAD_DATASETS=(OFF\|ON)` | `ON` | Download required datasets during build (only if they do not already exist in `pytorch-cpp/data`). |
|`-D CREATE_SCRIPTMODULES=(OFF\|ON)` | `OFF` | Create all required scriptmodule files for prelearned models / weights during build. Requires installed python3 with pytorch and torchvision. |
| `-D CMAKE_PREFIX_PATH=path/to/libtorch/share/cmake/Torch` | `<empty>` | Skip the downloading of LibTorch and use your own local version (see [Requirements](#requirements)) instead. |
| `-D CMAKE_BUILD_TYPE=(Release\|Debug\|...)` | `<empty>` | Determines the CMake build-type for single-configuration generators (see [CMake docs](https://cmake.org/cmake/help/latest/variable/CMAKE_BUILD_TYPE.html)).|
<details>
<summary><b>Example Linux</b></summary>
##### Aim
* Use existing Python, PyTorch (see [Requirements](#requirements)) and torchvision installation.
* Download all datasets and create all necessary scriptmodule files.
##### Command
```bash
cmake -B build \
-D CMAKE_BUILD_TYPE=Release \
-D CMAKE_PREFIX_PATH=/path/to/libtorch/share/cmake/Torch \
-D CREATE_SCRIPTMODULES=ON
```
</details>
<details>
<summary><b>Example Windows</b></summary>
##### Aim
* Automatically download LibTorch for CUDA 11.8 (Release version) and all necessary datasets.
* Do not create scriptmodule files.
##### Command
```bash
cmake -B build \
-A x64 \
-D CUDA_V=11.8
```
</details>
#### Build
>**_Note for Windows (Visual Studio) users:_** <br>
>The CMake script downloads the *Release* version of LibTorch, so `--config Release` has to be appended to the build command.
**How dataset download and scriptmodule creation work:**
* If `DOWNLOAD_DATASETS` is `ON`, the datasets required by the tutorials you choose to build will be downloaded to `pytorch-cpp/data` (if they do not already exist there).
* If `CREATE_SCRIPTMODULES` is `ON`, the scriptmodule files for the prelearned models / weights required by the tutorials you choose to build will be created in the `model` folder of the respective tutorial's source folder (if they do not already exist).
#### All tutorials
To build all tutorials use
```bash
cmake --build build
```
#### All tutorials in a category
You can choose to only build tutorials in one of the categories `basics`, `intermediate`, `advanced` or `popular`. For example, if you are only interested in the `basics` tutorials:
```bash
cmake --build build --target basics
# In general: cmake --build build --target {category}
```
#### Single tutorial
You can also choose to only build a single tutorial. For example to build the language model tutorial only:
```bash
cmake --build build --target language-model
# In general: cmake --build build --target {tutorial-name}
```
>**_Note_**:
> The target argument is the tutorial's foldername with all underscores replaced by hyphens.
>**_Tip for users of CMake version >= 3.15_**:
> You can specify several targets separated by spaces, for example:
> ```bash
> cmake --build build --target language-model image-captioning
> ```
#### Run Tutorials
1. (**IMPORTANT!**) First change into the tutorial's directory within `build/tutorials`. For example, assuming you are in the `pytorch-cpp` directory and want to change to the pytorch basics tutorial folder:
```bash
cd build/tutorials/basics/pytorch_basics
C++ Implementation of PyTorch Tutorials for Everyone.zip （128个子文件） 
AUTHORS 234B fetch_libtorch.cmake 2KB fetch_mnist.cmake 2KB fetch_flickr8k.cmake 2KB fetch_cifar10.cmake 2KB fetch_neural_style_transfer_images.cmake 1KB cpplint.cmake 1KB fetch_imagenette.cmake 1KB fetch_penntreebank.cmake 895B find_gz_extractor.cmake 839B copy_torch_dlls.cmake 799B check_files.cmake 763B create_torch_dll_hardlinks.cmake 423B fetch_datasets.cmake 350B CODEOWNERS 96B main.cpp 16KB main.cpp 11KB decoder_rnn.cpp 8KB main.cpp 6KB image_io.cpp 6KB main.cpp 5KB main.cpp 5KB main.cpp 5KB main.cpp 4KB main.cpp 4KB main.cpp 4KB data_utils.cpp 4KB main.cpp 4KB main.cpp 4KB score.cpp 4KB main.cpp 4KB main.cpp 4KB vggnet.cpp 4KB cifar10.cpp 3KB cifar10.cpp 3KB caption_dataset.cpp 3KB transform.cpp 3KB main.cpp 2KB main.cpp 2KB main.cpp 2KB imagefolder_dataset.cpp 2KB encoder_cnn.cpp 2KB main.cpp 2KB transform.cpp 2KB variational_autoencoder.cpp 2KB bi_rnn.cpp 1KB nnet.cpp 1KB residual_block.cpp 1KB corpus.cpp 1KB rnn_lm.cpp 997B nnet.cpp 892B vocabulary.cpp 798B convnet.cpp 589B rnn.cpp 575B dictionary.cpp 465B neural_net.cpp 464B main.cpp 205B Dockerfile 2KB .dockerignore 147B .gitattributes 69B .gitignore 671B validate.h 8KB scheduler.h 3KB resnet.h 3KB caption_dataset.h 3KB transform.h 2KB decoder_rnn.h 2KB transform.h 2KB cifar10.h 1KB cifar10.h 1KB score.h 1KB data_utils.h 1KB vggnet.h 1KB convnet.h 1KB imagefolder_dataset.h 988B encoder_cnn.h 748B image_io.h 722B variational_autoencoder.h 722B residual_block.h 694B vocabulary.h 594B rnn_lm.h 528B dictionary.h 488B corpus.h 446B nnet.h 415B nnet.h 401B bi_rnn.h 369B neural_net.h 364B rnn.h 363B pytorch_cpp_colab_notebook.ipynb 30KB tensor_slicing.ipynb 11KB LICENSE 1KB README.md 10KB CONTRIBUTING.md 2KB bug_report.md 660B feature_request.md 613B README.md 581B PULL_REQUEST_TEMPLATE.md 532B
pytorch_cpp.png 98KB create_encoder_cnn_backbone_scriptmodule.py 1KB create_resnet18_scriptmodule.py 1KB共 128 条
- 1
- 2
资源评论
