/vision

Datasets, Transforms and Models specific to Computer Vision

Primary LanguageJupyter NotebookBSD 3-Clause "New" or "Revised" LicenseBSD-3-Clause

torchvision

https://travis-ci.org/pytorch/vision.svg?branch=master https://pepy.tech/badge/torchvision https://img.shields.io/badge/dynamic/json.svg?label=docs&url=https%3A%2F%2Fpypi.org%2Fpypi%2Ftorchvision%2Fjson&query=%24.info.version&colorB=brightgreen&prefix=v

The torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision.

Installation

TorchVision requires PyTorch 1.1 or newer.

Anaconda:

conda install torchvision -c pytorch

pip:

pip install torchvision

From source:

python setup.py install
# or, for OSX
# MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ python setup.py install

By default, GPU support is built if CUDA is found and torch.cuda.is_available() is true. It's possible to force building GPU support by setting FORCE_CUDA=1 environment variable, which is useful when building a docker image.

Image Backend

Torchvision currently supports the following image backends:

  • Pillow (default)
  • Pillow-SIMD - a much faster drop-in replacement for Pillow with SIMD. If installed will be used as the default.
  • accimage - if installed can be activated by calling torchvision.set_image_backend('accimage')

C++ API

TorchVision also offers a C++ API that contains C++ equivalent of python models.

Installation From source:

mkdir build
cd build
cmake ..
make
make install

Documentation

You can find the API documentation on the pytorch website: http://pytorch.org/docs/master/torchvision/

Contributing

We appreciate all contributions. If you are planning to contribute back bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please first open an issue and discuss the feature with us.