The torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision. We recommend Anaconda as Python package management system. Torchvision currently supports Pillow (default), Pillow-SIMD, which is a much faster drop-in replacement for Pillow with SIMD, if installed will be used as the default. Also, accimage, if installed can be activated by calling torchvision.set_image_backend('accimage'), libpng, which can be installed via conda conda install libpng or any of the package managers for debian-based and RHEL-based Linux distributions, and libjpeg, which can be installed via conda conda install jpeg or any of the package managers for debian-based and RHEL-based Linux distributions. It supports libjpeg-turbo as well. libpng and libjpeg must be available at compilation time in order to be available. TorchVision also offers a C++ API that contains C++ equivalent of python models.
Features
- This is a utility library that downloads and prepares public datasets
- TorchVision offers a C++ API that contains C++ equivalent of python models
- Once installed, the library can be accessed in cmake
- The TorchVision package will also automatically look for the Torch package and add it as a dependency
- In order to get the torchvision operators registered with torch ensure that you #include <torchvision/vision.h> in your project
- You can find the API documentation on the pytorch website
Project Samples
