torchvision

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

Installation

We recommend Anaconda as Python package management system. Please refer to pytorch.org for the detail of PyTorch (torch) installation. The following is the corresponding torchvision versions and supported Python versions.

torch	torchvision	python
main / nightly	main / nightly	>=3.6, <=3.9
1.9.0	0.10.0	>=3.6, <=3.9
1.8.1	0.9.1	>=3.6, <=3.9
1.8.0	0.9.0	>=3.6, <=3.9
1.7.1	0.8.2	>=3.6, <=3.9
1.7.0	0.8.1	>=3.6, <=3.8
1.7.0	0.8.0	>=3.6, <=3.8
1.6.0	0.7.0	>=3.6, <=3.8
1.5.1	0.6.1	>=3.5, <=3.8
1.5.0	0.6.0	>=3.5, <=3.8
1.4.0	0.5.0	==2.7, >=3.5, <=3.8
1.3.1	0.4.2	==2.7, >=3.5, <=3.7
1.3.0	0.4.1	==2.7, >=3.5, <=3.7
1.2.0	0.4.0	==2.7, >=3.5, <=3.7
1.1.0	0.3.0	==2.7, >=3.5, <=3.7
<=1.0.1	0.2.2	==2.7, >=3.5, <=3.7

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

In case building TorchVision from source fails, install the nightly version of PyTorch following the linked guide on the contributing page and retry the 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')
libpng - can be installed via conda conda install libpng or any of the package managers for debian-based and RHEL-based Linux distributions.
libjpeg - can be installed via conda conda install jpeg or any of the package managers for debian-based and RHEL-based Linux distributions. libjpeg-turbo can be used as well.

Notes: libpng and libjpeg must be available at compilation time in order to be available. Make sure that it is available on the standard library locations, otherwise, add the include and library paths in the environment variables TORCHVISION_INCLUDE and TORCHVISION_LIBRARY, respectively.

Video Backend

Torchvision currently supports the following video backends:

[pyav](https://github.com/PyAV-Org/PyAV) (default) - Pythonic binding for ffmpeg libraries.
video_reader - This needs ffmpeg to be installed and torchvision to be built from source. There shouldn’t be any conflicting version of ffmpeg installed. Currently, this is only supported on Linux.

conda install -c conda-forge ffmpeg
python setup.py install

Using the models on C++

TorchVision provides an example project for how to use the models on C++ using JIT Script.

Installation From source:

mkdir build
cd build
# Add -DWITH_CUDA=on support for the CUDA if needed
cmake ..
make
make install

Once installed, the library can be accessed in cmake (after properly configuring CMAKE_PREFIX_PATH) via the TorchVision::TorchVision target:

find_package(TorchVision REQUIRED)
target_link_libraries(my-target PUBLIC TorchVision::TorchVision)

The TorchVision package will also automatically look for the Torch package and add it as a dependency to my-target, so make sure that it is also available to cmake via the CMAKE_PREFIX_PATH.

For an example setup, take a look at examples/cpp/hello_world.

TorchVision Operators

In order to get the torchvision operators registered with torch (eg. for the JIT), all you need to do is to ensure that you #include <torchvision/vision.h> in your project.

Documentation

You can find the API documentation on the pytorch website: https://pytorch.org/vision/stable/index.html

Contributing

See the CONTRIBUTING file for how to help out.

Disclaimer on Datasets

This is a utility library that downloads and prepares public datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have license to use the dataset. It is your responsibility to determine whether you have permission to use the dataset under the dataset’s license.

If you’re a dataset owner and wish to update any part of it (description, citation, etc.), or do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thanks for your contribution to the ML community!

Release files for torchvision 0.11.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for torchvision 0.11.2
File	Interpreter	ABI	Platform	Reset
torchvision-0.11.2-cp39-cp39-win_amd64.whl 985.0 kB Dec 15, 2021	CPython 3.9	CPython 3.9	Windows x86-64	Details
torchvision-0.11.2-cp39-cp39-manylinux2014_aarch64.whl 614.0 kB Dec 15, 2021	CPython 3.9	CPython 3.9	Linux glibc 2.17+ ARM64	Details
torchvision-0.11.2-cp39-cp39-manylinux1_x86_64.whl 23.2 MB Dec 15, 2021	CPython 3.9	CPython 3.9	Linux glibc 2.5+ x86-64	Details
torchvision-0.11.2-cp39-cp39-macosx_11_0_arm64.whl 552.3 kB Dec 15, 2021	CPython 3.9	CPython 3.9	macOS 11.0+ ARM64	Details
torchvision-0.11.2-cp39-cp39-macosx_10_9_x86_64.whl 1.2 MB Dec 15, 2021	CPython 3.9	CPython 3.9	macOS 10.9+ x86-64	Details
torchvision-0.11.2-cp38-cp38-win_amd64.whl 985.0 kB Dec 15, 2021	CPython 3.8	CPython 3.8	Windows x86-64	Details
torchvision-0.11.2-cp38-cp38-manylinux2014_aarch64.whl 14.7 MB Dec 15, 2021	CPython 3.8	CPython 3.8	Linux glibc 2.17+ ARM64	Details
torchvision-0.11.2-cp38-cp38-manylinux1_x86_64.whl 23.3 MB Dec 15, 2021	CPython 3.8	CPython 3.8	Linux glibc 2.5+ x86-64	Details
torchvision-0.11.2-cp38-cp38-macosx_11_0_arm64.whl 597.5 kB Dec 15, 2021	CPython 3.8	CPython 3.8	macOS 11.0+ ARM64	Details
torchvision-0.11.2-cp38-cp38-macosx_10_9_x86_64.whl 1.2 MB Dec 15, 2021	CPython 3.8	CPython 3.8	macOS 10.9+ x86-64	Details
torchvision-0.11.2-cp37-cp37m-win_amd64.whl 985.0 kB Dec 15, 2021	CPython 3.7	CPython 3.7 pymalloc	Windows x86-64	Details
torchvision-0.11.2-cp37-cp37m-manylinux2014_aarch64.whl 14.7 MB Dec 15, 2021	CPython 3.7	CPython 3.7 pymalloc	Linux glibc 2.17+ ARM64	Details
torchvision-0.11.2-cp37-cp37m-manylinux1_x86_64.whl 23.3 MB Dec 15, 2021	CPython 3.7	CPython 3.7 pymalloc	Linux glibc 2.5+ x86-64	Details
torchvision-0.11.2-cp37-cp37m-macosx_10_9_x86_64.whl 1.2 MB Dec 15, 2021	CPython 3.7	CPython 3.7 pymalloc	macOS 10.9+ x86-64	Details
torchvision-0.11.2-cp36-cp36m-win_amd64.whl 985.2 kB Dec 15, 2021	CPython 3.6	CPython 3.6 pymalloc	Windows x86-64	Details
torchvision-0.11.2-cp36-cp36m-manylinux2014_aarch64.whl 14.7 MB Dec 15, 2021	CPython 3.6	CPython 3.6 pymalloc	Linux glibc 2.17+ ARM64	Details
torchvision-0.11.2-cp36-cp36m-manylinux1_x86_64.whl 23.3 MB Dec 15, 2021	CPython 3.6	CPython 3.6 pymalloc	Linux glibc 2.5+ x86-64	Details
torchvision-0.11.2-cp36-cp36m-macosx_10_9_x86_64.whl 1.2 MB Dec 15, 2021	CPython 3.6	CPython 3.6 pymalloc	macOS 10.9+ x86-64	Details

Total release size: 147.6 MB

Release files / torchvision-0.11.2-cp39-cp39-win_amd64.whl

Download URL	torchvision-0.11.2-cp39-cp39-win_amd64.whl
Size	985.0 kB
Tags	CPython 3.9 Windows x86-64
SHA-256 checksum How to use checksums	`b78b753b01c19f60bf4df078d245609ed6df9265a127d9fbc2ca202409779cda`
BLAKE2b-256 checksum How to use checksums	`3aadbfe05d5c85e8fcc343b15acc2bb365e7af01d39ba8b6adf680356bac72e7`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp39-cp39-manylinux2014_aarch64.whl

Download URL	torchvision-0.11.2-cp39-cp39-manylinux2014_aarch64.whl
Size	614.0 kB
Tags	CPython 3.9 Linux glibc 2.17+ ARM64
SHA-256 checksum How to use checksums	`3315176f2ee887dcb9d4ada02d103bad837ba065c84d992dce0dbf9dae9ad43c`
BLAKE2b-256 checksum How to use checksums	`3c11a90c538b557abd33955c961f7bc230a2b6d4ef24ecb9e1d2a7a6d479d307`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp39-cp39-manylinux1_x86_64.whl

Download URL	torchvision-0.11.2-cp39-cp39-manylinux1_x86_64.whl
Size	23.2 MB
Tags	CPython 3.9 Linux glibc 2.5+ x86-64
SHA-256 checksum How to use checksums	`bc6b125134278d8b59682a3693bbf99a1eac6306f0eb71314333010d28392a83`
BLAKE2b-256 checksum How to use checksums	`928bcbbcf8e055b074ea55ae07d1f3d8fb2888d47f2944ee5ea286243d4d2ba2`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp39-cp39-macosx_11_0_arm64.whl

Download URL	torchvision-0.11.2-cp39-cp39-macosx_11_0_arm64.whl
Size	552.3 kB
Tags	CPython 3.9 macOS 11.0+ ARM64
SHA-256 checksum How to use checksums	`eb479be61a28fcff71b1e3ec823641cd75d61229bedab1e83659e3df53ca0159`
BLAKE2b-256 checksum How to use checksums	`088bae35ded85a6bf8d79583dad7f62f507ed3cd6637cd0944a10e2569f6e0b3`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.3.0 pkginfo/1.7.0 requests/2.24.0 setuptools/50.3.1.post20201107 requests-toolbelt/0.9.1 tqdm/4.51.0 CPython/3.8.5`

Release files / torchvision-0.11.2-cp39-cp39-macosx_10_9_x86_64.whl

Download URL	torchvision-0.11.2-cp39-cp39-macosx_10_9_x86_64.whl
Size	1.2 MB
Tags	CPython 3.9 macOS 10.9+ x86-64
SHA-256 checksum How to use checksums	`63d6f46e083f00ad7ce09d355eb94f512bf41899630240c6c865ca0d9d00718c`
BLAKE2b-256 checksum How to use checksums	`73f2b360ddc86b4b0e10750f1dcf95542c978f6a7893220af245a8e04a0d5664`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp38-cp38-win_amd64.whl

Download URL	torchvision-0.11.2-cp38-cp38-win_amd64.whl
Size	985.0 kB
Tags	CPython 3.8 Windows x86-64
SHA-256 checksum How to use checksums	`27f0d9088c76edfa3c1f1dcaf965f102437c049f13b599ef02abe99f4d346cb6`
BLAKE2b-256 checksum How to use checksums	`f472e8011d274951d2ec3155b079b97fc61c2c8a293061dda9b327552b9d32f7`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp38-cp38-manylinux2014_aarch64.whl

Download URL	torchvision-0.11.2-cp38-cp38-manylinux2014_aarch64.whl
Size	14.7 MB
Tags	CPython 3.8 Linux glibc 2.17+ ARM64
SHA-256 checksum How to use checksums	`ecf3f8f8e548dd7b36c5abca03563a32a6d5cb7e97ceec012df1b6380ed5d4c3`
BLAKE2b-256 checksum How to use checksums	`3d125c4b99fb9831d47520ba08de93c10e8de9c0514f4156a420b6fde9276ae0`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp38-cp38-manylinux1_x86_64.whl

Download URL	torchvision-0.11.2-cp38-cp38-manylinux1_x86_64.whl
Size	23.3 MB
Tags	CPython 3.8 Linux glibc 2.5+ x86-64
SHA-256 checksum How to use checksums	`82431c4cf9cce36d6ec5f338b4cc5b96732a4becb359588bbc72fba282d3cfff`
BLAKE2b-256 checksum How to use checksums	`36c64f850a3848b2c863ebe8abd3dfa6b58fdc84544a244fb96e2446b60bf7ec`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp38-cp38-macosx_11_0_arm64.whl

Download URL	torchvision-0.11.2-cp38-cp38-macosx_11_0_arm64.whl
Size	597.5 kB
Tags	CPython 3.8 macOS 11.0+ ARM64
SHA-256 checksum How to use checksums	`3abcfab98dea4bc1e512e99c5b56e66e237bd65569e1c9b1c3c2d459ef50795c`
BLAKE2b-256 checksum How to use checksums	`6feb67ad3c5796753a7e9928c3329427b59fb879a1a24e0bea8624ee59638820`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.3.0 pkginfo/1.7.0 requests/2.24.0 setuptools/50.3.1.post20201107 requests-toolbelt/0.9.1 tqdm/4.51.0 CPython/3.8.5`

Release files / torchvision-0.11.2-cp38-cp38-macosx_10_9_x86_64.whl

Download URL	torchvision-0.11.2-cp38-cp38-macosx_10_9_x86_64.whl
Size	1.2 MB
Tags	CPython 3.8 macOS 10.9+ x86-64
SHA-256 checksum How to use checksums	`52b14ce23a6e0a5a1309970888a1febb12e93fe6aed78df8aa115f1cf2019cc6`
BLAKE2b-256 checksum How to use checksums	`0829f8ff498296dc8d2bc8c51c07fc8f3a069cd188c7c4ba343cb1118869b328`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp37-cp37m-win_amd64.whl

Download URL	torchvision-0.11.2-cp37-cp37m-win_amd64.whl
Size	985.0 kB
Tags	CPython 3.7 CPython 3.7 pymalloc Windows x86-64
SHA-256 checksum How to use checksums	`d2aa1e253c9ddcf728a2dc6e771ebaf3201798cf91304cd352795a34daefce51`
BLAKE2b-256 checksum How to use checksums	`5fcf7100087a34cc1a4fd6aa492edd2fe7c51c6773bad6473bc2551c427834cb`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp37-cp37m-manylinux2014_aarch64.whl

Download URL	torchvision-0.11.2-cp37-cp37m-manylinux2014_aarch64.whl
Size	14.7 MB
Tags	CPython 3.7 CPython 3.7 pymalloc Linux glibc 2.17+ ARM64
SHA-256 checksum How to use checksums	`fe1395b5fe3b5f2111312a8c75dd48176db7b9f129e1f4159bf1fb2aeec54778`
BLAKE2b-256 checksum How to use checksums	`18023da9c183a5ff153014a86b4c8ed6dd4f7ac4fe4e429729c534b3823ae44a`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp37-cp37m-manylinux1_x86_64.whl

Download URL	torchvision-0.11.2-cp37-cp37m-manylinux1_x86_64.whl
Size	23.3 MB
Tags	CPython 3.7 CPython 3.7 pymalloc Linux glibc 2.5+ x86-64
SHA-256 checksum How to use checksums	`32cca2b5e0696f59e03c1261444deb81c87c6967d444aaf2d156f3023e741ffe`
BLAKE2b-256 checksum How to use checksums	`8cf73e3875ce0155d9a2acf9911bc80679bdccfa81cc6f3c83fec7c2b267f46a`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp37-cp37m-macosx_10_9_x86_64.whl

Download URL	torchvision-0.11.2-cp37-cp37m-macosx_10_9_x86_64.whl
Size	1.2 MB
Tags	CPython 3.7 CPython 3.7 pymalloc macOS 10.9+ x86-64
SHA-256 checksum How to use checksums	`3091e5d3131e0664ca817ef32eff0ec5f79e2f0d61b447ae63bdd2429aff179c`
BLAKE2b-256 checksum How to use checksums	`7f02de14c5b6bae9d407a9aa4fffff001fc68b2066e7787e232069649b70ddcc`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp36-cp36m-win_amd64.whl

Download URL	torchvision-0.11.2-cp36-cp36m-win_amd64.whl
Size	985.2 kB
Tags	CPython 3.6 CPython 3.6 pymalloc Windows x86-64
SHA-256 checksum How to use checksums	`6d84490010761a34d6238987f88f8bccec06914431fc13c221902ea4f54ecb43`
BLAKE2b-256 checksum How to use checksums	`f4cb989e29a5e0f74a72e0f919587bb80e36647a60309fc39183e732b9c5bd12`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp36-cp36m-manylinux2014_aarch64.whl

Download URL	torchvision-0.11.2-cp36-cp36m-manylinux2014_aarch64.whl
Size	14.7 MB
Tags	CPython 3.6 CPython 3.6 pymalloc Linux glibc 2.17+ ARM64
SHA-256 checksum How to use checksums	`12eb97a2b87661914c2a6743ec535b432194b3a17620217cab201733e63d0a8f`
BLAKE2b-256 checksum How to use checksums	`9e813f93005f4b5815cb5e4938c3ad267c6542ff40e69c683a09e2e042107976`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp36-cp36m-manylinux1_x86_64.whl

Download URL	torchvision-0.11.2-cp36-cp36m-manylinux1_x86_64.whl
Size	23.3 MB
Tags	CPython 3.6 CPython 3.6 pymalloc Linux glibc 2.5+ x86-64
SHA-256 checksum How to use checksums	`a33c4e5c8456d3cdbb706636f209f318c8544be0f08179056296765db95b981b`
BLAKE2b-256 checksum How to use checksums	`3803c963ecdf98fae15286437ae533750e2c39e988b7d8c86fad4dbc73a3a146`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`

Release files / torchvision-0.11.2-cp36-cp36m-macosx_10_9_x86_64.whl

Download URL	torchvision-0.11.2-cp36-cp36m-macosx_10_9_x86_64.whl
Size	1.2 MB
Tags	CPython 3.6 CPython 3.6 pymalloc macOS 10.9+ x86-64
SHA-256 checksum How to use checksums	`0f52745f652fe82e962e3399ac19f5ce7fe42e2b6bf73ef24f4aa1f222bbbfca`
BLAKE2b-256 checksum How to use checksums	`08691b6ce41f626c87e839014e4be04bf2d007ec13b9aff7b8a90eddb5abf412`
Upload date	Dec 15, 2021
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/3.7.3 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.9.1`