image and video datasets and models for torch deep learning

These details have been verified by PyPI

Maintainers

atalman ezyang facebook malfet seemethere soumith

Project description

torchvision

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

Installation

Please refer to the official instructions to install the stable versions of torch and torchvision on your system.

To build source, refer to our contributing page.

The following is the corresponding torchvision versions and supported Python versions.

`torch`	`torchvision`	Python
`main` / `nightly`	`main` / `nightly`	`>=3.9`, `<=3.12`
`2.5`	`0.20`	`>=3.9`, `<=3.12`
`2.4`	`0.19`	`>=3.8`, `<=3.12`
`2.3`	`0.18`	`>=3.8`, `<=3.12`
`2.2`	`0.17`	`>=3.8`, `<=3.11`
`2.1`	`0.16`	`>=3.8`, `<=3.11`
`2.0`	`0.15`	`>=3.8`, `<=3.11`

older versions

`torch`	`torchvision`	Python
`1.13`	`0.14`	`>=3.7.2`, `<=3.10`
`1.12`	`0.13`	`>=3.7`, `<=3.10`
`1.11`	`0.12`	`>=3.7`, `<=3.10`
`1.10`	`0.11`	`>=3.6`, `<=3.9`
`1.9`	`0.10`	`>=3.6`, `<=3.9`
`1.8`	`0.9`	`>=3.6`, `<=3.9`
`1.7`	`0.8`	`>=3.6`, `<=3.9`
`1.6`	`0.7`	`>=3.6`, `<=3.8`
`1.5`	`0.6`	`>=3.5`, `<=3.8`
`1.4`	`0.5`	`==2.7`, `>=3.5`, `<=3.8`
`1.3`	`0.4.2` / `0.4.3`	`==2.7`, `>=3.5`, `<=3.7`
`1.2`	`0.4.1`	`==2.7`, `>=3.5`, `<=3.7`
`1.1`	`0.3`	`==2.7`, `>=3.5`, `<=3.7`
`<=1.0`	`0.2`	`==2.7`, `>=3.5`, `<=3.7`

Image Backends

Torchvision currently supports the following image backends:

torch tensors
PIL images:
- Pillow
- Pillow-SIMD - a much faster drop-in replacement for Pillow with SIMD.

[UNSTABLE] Video Backend

Torchvision currently supports the following video backends:

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<4.3'
python setup.py install

Using the models on C++

Refer to example/cpp.

DISCLAIMER: the libtorchvision library includes the torchvision custom ops as well as most of the C++ torchvision APIs. Those APIs do not come with any backward-compatibility guarantees and may change from one version to the next. Only the Python APIs are stable and with backward-compatibility guarantees. So, if you need stability within a C++ environment, your best bet is to export the Python APIs via torchscript.

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!

Pre-trained Model License

The pre-trained models provided in this library may have their own licenses or terms and conditions derived from the dataset used for training. It is your responsibility to determine whether you have permission to use the models for your use case.

More specifically, SWAG models are released under the CC-BY-NC 4.0 license. See SWAG LICENSE for additional details.

Citing TorchVision

If you find TorchVision useful in your work, please consider citing the following BibTeX entry:

@software{torchvision2016,
    title        = {TorchVision: PyTorch's Computer Vision library},
    author       = {TorchVision maintainers and contributors},
    year         = 2016,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/pytorch/vision}}
}

Project details

These details have been verified by PyPI

Maintainers

atalman ezyang facebook malfet seemethere soumith

Release history Release notifications | RSS feed

This version

0.21.0

Jan 29, 2025

0.20.1

Oct 29, 2024

0.20.0

Oct 17, 2024

0.19.1

Sep 4, 2024

0.19.0

Jul 24, 2024

0.18.1

Jun 5, 2024

0.18.0

Apr 24, 2024

0.17.2

Mar 27, 2024

0.17.1

Feb 22, 2024

0.17.0

Jan 30, 2024

0.16.2

Dec 14, 2023

0.16.1

Nov 15, 2023

0.16.0

Oct 4, 2023

0.15.2

May 8, 2023

0.15.1

Mar 15, 2023

0.15.0 yanked

Mar 15, 2023

Reason this release was yanked:

Contains an incorrect torch dependency

0.14.1

Dec 15, 2022

0.14.0

Oct 28, 2022

0.13.1

Aug 5, 2022

0.13.0

Jun 28, 2022

0.12.0

Mar 10, 2022

0.11.3

Jan 27, 2022

0.11.2

Dec 15, 2021

0.11.1

Oct 21, 2021

0.11.0 yanked

Oct 21, 2021

Reason this release was yanked:

Dependency issue, depends on a version of torch that does not exist on pypi

0.10.1

Sep 20, 2021

0.10.0

Jun 15, 2021

0.9.1

Mar 25, 2021

0.9.0

Mar 4, 2021

0.8.2

Dec 10, 2020

0.8.1

Oct 27, 2020

0.8.0

Oct 27, 2020

0.7.0

Jul 28, 2020

0.6.1

Jun 18, 2020

0.6.0

Apr 21, 2020

0.5.0

Jan 15, 2020

0.4.2

Nov 7, 2019

0.4.1.post2

Oct 22, 2019

0.4.1

Oct 10, 2019

0.4.0

Aug 8, 2019

0.3.0

May 22, 2019

0.2.2.post3 yanked

Mar 1, 2019

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.2.2.post2 yanked

Feb 28, 2019

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.2.2 yanked

Feb 27, 2019

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.2.1 yanked

Apr 24, 2018

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.2.0 yanked

Dec 5, 2017

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.1.9 yanked

Aug 6, 2017

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.1.8 yanked

Mar 29, 2017

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.1.7 yanked

Jan 19, 2017

Reason this release was yanked:

So that users won't accidentally install this when using python 3.11

0.1.6 yanked

Jan 18, 2017

Reason this release was yanked:

0.1.6 is past it's support date and confuses users on unsupported platforms

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

torchvision-0.21.0-cp313-cp313-win_amd64.whl (1.6 MB view details)

Uploaded Jan 29, 2025 CPython 3.13 Windows x86-64

torchvision-0.21.0-cp313-cp313-manylinux_2_28_aarch64.whl (2.3 MB view details)

Uploaded Jan 29, 2025 CPython 3.13 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-cp313-cp313-manylinux1_x86_64.whl (7.2 MB view details)

Uploaded Jan 29, 2025 CPython 3.13

torchvision-0.21.0-cp313-cp313-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Jan 29, 2025 CPython 3.13 macOS 11.0+ ARM64

torchvision-0.21.0-cp312-cp312-win_amd64.whl (1.6 MB view details)

Uploaded Jan 29, 2025 CPython 3.12 Windows x86-64

torchvision-0.21.0-cp312-cp312-manylinux_2_28_aarch64.whl (14.7 MB view details)

Uploaded Jan 29, 2025 CPython 3.12 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-cp312-cp312-manylinux1_x86_64.whl (7.2 MB view details)

Uploaded Jan 29, 2025 CPython 3.12

torchvision-0.21.0-cp312-cp312-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Jan 29, 2025 CPython 3.12 macOS 11.0+ ARM64

torchvision-0.21.0-cp311-cp311-win_amd64.whl (1.6 MB view details)

Uploaded Jan 29, 2025 CPython 3.11 Windows x86-64

torchvision-0.21.0-cp311-cp311-manylinux_2_28_aarch64.whl (14.7 MB view details)

Uploaded Jan 29, 2025 CPython 3.11 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-cp311-cp311-manylinux1_x86_64.whl (7.2 MB view details)

Uploaded Jan 29, 2025 CPython 3.11

torchvision-0.21.0-cp311-cp311-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Jan 29, 2025 CPython 3.11 macOS 11.0+ ARM64

torchvision-0.21.0-cp310-cp310-win_amd64.whl (1.6 MB view details)

Uploaded Jan 29, 2025 CPython 3.10 Windows x86-64

torchvision-0.21.0-cp310-cp310-manylinux_2_28_aarch64.whl (14.7 MB view details)

Uploaded Jan 29, 2025 CPython 3.10 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-cp310-cp310-manylinux1_x86_64.whl (7.2 MB view details)

Uploaded Jan 29, 2025 CPython 3.10

torchvision-0.21.0-cp310-cp310-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Jan 29, 2025 CPython 3.10 macOS 11.0+ ARM64

torchvision-0.21.0-cp39-cp39-win_amd64.whl (1.6 MB view details)

Uploaded Jan 29, 2025 CPython 3.9 Windows x86-64

torchvision-0.21.0-cp39-cp39-manylinux_2_28_aarch64.whl (2.3 MB view details)

Uploaded Jan 29, 2025 CPython 3.9 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-cp39-cp39-manylinux1_x86_64.whl (7.2 MB view details)

Uploaded Jan 29, 2025 CPython 3.9

torchvision-0.21.0-cp39-cp39-macosx_11_0_arm64.whl (1.8 MB view details)

Uploaded Jan 29, 2025 CPython 3.9 macOS 11.0+ ARM64

torchvision-0.21.0-1-cp313-cp313-manylinux_2_28_aarch64.whl (2.3 MB view details)

Uploaded Mar 18, 2025 CPython 3.13 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-1-cp312-cp312-manylinux_2_28_aarch64.whl (2.3 MB view details)

Uploaded Mar 18, 2025 CPython 3.12 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-1-cp311-cp311-manylinux_2_28_aarch64.whl (2.3 MB view details)

Uploaded Mar 18, 2025 CPython 3.11 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-1-cp310-cp310-manylinux_2_28_aarch64.whl (2.3 MB view details)

Uploaded Mar 18, 2025 CPython 3.10 manylinux: glibc 2.28+ ARM64

torchvision-0.21.0-1-cp39-cp39-manylinux_2_28_aarch64.whl (2.3 MB view details)

Uploaded Mar 18, 2025 CPython 3.9 manylinux: glibc 2.28+ ARM64

File details

Details for the file torchvision-0.21.0-cp313-cp313-win_amd64.whl.

File metadata

Download URL: torchvision-0.21.0-cp313-cp313-win_amd64.whl
Upload date: Jan 29, 2025
Size: 1.6 MB
Tags: CPython 3.13, Windows x86-64
Uploaded using Trusted Publishing? No
Uploaded via: twine/5.0.0 CPython/3.11.7

File hashes

Hashes for torchvision-0.21.0-cp313-cp313-win_amd64.whl
Algorithm	Hash digest
SHA256	`9147f5e096a9270684e3befdee350f3cacafd48e0c54ab195f45790a9c146d67`
MD5	`82f6996027b6dcebbd81dd1fc4dfe3fc`
BLAKE2b-256	`edb4fc60e3bc003879d3de842baea258fffc3586f4b49cd435a5ba1e09c33315`

Algorithm	Hash digest
SHA256	`5045a3a5f21ec3eea6962fa5f2fa2d4283f854caec25ada493fcf4aab2925467`
MD5	`62317750fcc5738a5759db63f8d36c51`
BLAKE2b-256	`0b2d3c3ee10608310a395594aac7da8640372ed79c6585910ccae6919658dcdc`

Algorithm	Hash digest
SHA256	`084ac3f5a1f50c70d630a488d19bf62f323018eae1b1c1232f2b7047d3a7b76d`
MD5	`264997403924e65f6d43aeb981c32821`
BLAKE2b-256	`cb4c99880813aa50e64447fb1c4c6c804a793d2d78f7f7c53e99ddee7fa175fa`

Algorithm	Hash digest
SHA256	`659b76c86757cb2ee4ca2db245e0740cfc3081fef46f0f1064d11adb4a8cee31`
MD5	`8b2cbbaeb15ae79a8d7b2f448ca23bc2`
BLAKE2b-256	`f95647d456b61c3bbce7bed4af3925c83d405bb87468e659fd3cf3d9840c3b51`

Algorithm	Hash digest
SHA256	`6eb75d41e3bbfc2f7642d0abba9383cc9ae6c5a4ca8d6b00628c225e1eaa63b3`
MD5	`c62d69984dd2a44bca11e1a76a423033`
BLAKE2b-256	`4c6ac7752603060d076dfed95135b78b047dc71792630cbcb022e3693d6f32ef`

Algorithm	Hash digest
SHA256	`5083a5b1fec2351bf5ea9900a741d54086db75baec4b1d21e39451e00977f1b1`
MD5	`627e928e82ee44ecc394a2bde9b8a313`
BLAKE2b-256	`bbea03541ed901cdc30b934f897060d09bbf7a98466a08ad1680320f9ce0cbe0`

Algorithm	Hash digest
SHA256	`b578bcad8a4083b40d34f689b19ca9f7c63e511758d806510ea03c29ac568f7b`
MD5	`c4d125f45c1242bf6f17f894a615203a`
BLAKE2b-256	`36630722e153fd27d64d5b0af45b5c8cb0e80b35a68cf0130303bc9a8bb095c7`

Algorithm	Hash digest
SHA256	`97a5814a93c793aaf0179cfc7f916024f4b63218929aee977b645633d074a49f`
MD5	`b03810c0c53fe4e52e6f4ba3317e11bb`
BLAKE2b-256	`6e1b28f527b22d5e8800184d0bc847f801ae92c7573a8c15979d92b7091c0751`

Algorithm	Hash digest
SHA256	`49bcfad8cfe2c27dee116c45d4f866d7974bcf14a5a9fbef893635deae322f2f`
MD5	`d99926d02f42115a119f01cd23375f2c`
BLAKE2b-256	`88534ad334b9b1d8dd99836869fec139cb74a27781298360b91b9506c53f1d10`

Algorithm	Hash digest
SHA256	`54454923a50104c66a9ab6bd8b73a11c2fc218c964b1006d5d1fe5b442c3dcb6`
MD5	`796f69e6c3779105a457ffe1f0d5f7e5`
BLAKE2b-256	`8ca1ee962ef9d0b2bf7a6f8b14cb95acb70e05cd2101af521032a09e43f8582f`

Algorithm	Hash digest
SHA256	`3891cd086c5071bda6b4ee9d266bb2ac39c998c045c2ebcd1e818b8316fb5d41`
MD5	`dc1995a7c54c7b0901b87b062d0c5d94`
BLAKE2b-256	`bea2b0cedf0a411f1a5d75cfc0b87cde56dd1ddc1878be46a42c905cd8580220`

Algorithm	Hash digest
SHA256	`110d115333524d60e9e474d53c7d20f096dbd8a080232f88dddb90566f90064c`
MD5	`c4858c74b62d8c6cb64d37bd03d8cf79`
BLAKE2b-256	`298800c69db213ee2443ada8886ec60789b227e06bb869d85ee324578221a7f7`

Algorithm	Hash digest
SHA256	`abbf1d7b9d52c00d2af4afa8dac1fb3e2356f662a4566bd98dfaaa3634f4eb34`
MD5	`4d2458d2341e8aa37e37afd94cc9190d`
BLAKE2b-256	`aaf7799ddd538b21017cbf80294c92e9efbf6db08dff6efee37c3be114a81845`

Algorithm	Hash digest
SHA256	`54815e0a56dde95cc6ec952577f67e0dc151eadd928e8d9f6a7f821d69a4a734`
MD5	`c59e4662e0cfe1bcaabcf65cb509a3e0`
BLAKE2b-256	`0e6b4fca9373eda42c1b04096758306b7bd55f7d8f78ba273446490855a0f25d`

Algorithm	Hash digest
SHA256	`b0c0b264b89ab572888244f2e0bad5b7eaf5b696068fc0b93e96f7c3c198953f`
MD5	`ffa0625d58bba8ebefba7f2b2a73e33e`
BLAKE2b-256	`5e4432e2d2d174391374d5ff3c4691b802e8efda9ae27ab9062eca2255b006af`

Algorithm	Hash digest
SHA256	`044ea420b8c6c3162a234cada8e2025b9076fa82504758cd11ec5d0f8cd9fa37`
MD5	`8243c3951263128289fe84342d7e5294`
BLAKE2b-256	`8e0d143bd264876fad17c82096b6c2d433f1ac9b29cdc69ee45023096976ee3d`

Algorithm	Hash digest
SHA256	`8c44b6924b530d0702e88ff383b65c4b34a0eaf666e8b399a73245574d546947`
MD5	`732ff4726173690824554495f2a315e4`
BLAKE2b-256	`6d348b74ffdcb8e066b9abfc7a59407ae8fa9a67cb1e296f090d71bf4577f6cd`

Algorithm	Hash digest
SHA256	`6bdce3890fa949219de129e85e4f6d544598af3c073afe5c44e14aed15bdcbb2`
MD5	`f246fb16b7fea8d091810825d9cee869`
BLAKE2b-256	`a8536822bd507088419b44d95d40a165f83d635568044e2e40c8dd5ff48984b2`

Algorithm	Hash digest
SHA256	`e6572227228ec521618cea9ac3a368c45b7f96f1f8622dc9f1afe891c044051f`
MD5	`076decdbb7987a18b25d6ab4008b5a5c`
BLAKE2b-256	`b11e0c329d94f92c498f1b76eb283b2d26f244ea8631dee37b2566e20ff4724d`

Algorithm	Hash digest
SHA256	`5c22caeaae8b3c36d93459f1a5294e6f43306cff856ed243189a229331a404b4`
MD5	`e13e5f7608365b8fe24a47836991e827`
BLAKE2b-256	`49d5d18c5d89cbe32015b033f1fa06918c7cdd5c0af0c03e55d72a3cc2d768f8`

Algorithm	Hash digest
SHA256	`7e9e9afa150e40cd2a8f0701c43cb82a8d724f512896455c0918b987f94b84a4`
MD5	`e76ab853d1996773800e2c0dbea66371`
BLAKE2b-256	`4efe5e193353706dab96fe73ae100d5a633ff635ce310e0d92f3bc2958d075b1`

torchvision 0.21.0

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Project description

torchvision

Installation

Image Backends

[UNSTABLE] Video Backend

Using the models on C++

Documentation

Contributing

Disclaimer on Datasets

Pre-trained Model License

Citing TorchVision

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Release history Release notifications | RSS feed

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

Algorithm	Hash digest
SHA256	`ffa2a16499508fe6798323e455f312c7c55f2a88901c9a7c0fb1efa86cf7e327`
MD5	`d1e578e1d726c020773b3d317962e820`
BLAKE2b-256	`525b76ca113a853b19c7b1da761f8a72cb6429b3bd0bf932537d8df4657f47c3`

Algorithm	Hash digest
SHA256	`ff96666b94a55e802ea6796cabe788541719e6f4905fc59c380fed3517b6a64d`
MD5	`a5ae261cae6b28f4afe583fe6de6635b`
BLAKE2b-256	`4e3db7241abfa3e6651c6e00796f5de2bd1ce4d500bf5159bcbfeea47e711b93`

Algorithm	Hash digest
SHA256	`5568c5a1ff1b2ec33127b629403adb530fab81378d9018ca4ed6508293f76e2b`
MD5	`70952857f58424a6cdd48a506b5fb166`
BLAKE2b-256	`a92072eb0b5b08fa293f20fc41c374e37cf899f0033076f0144d2cdc48f9faee`

Algorithm	Hash digest
SHA256	`669575b290ec27304569e188a960d12b907d5173f9cd65e86621d34c4e5b6c30`
MD5	`98b5a86b181cac8c3b76891f1a18eaef`
BLAKE2b-256	`37ae4ecf9177702d29b51b70b733dad00f79d6fbb5e579ab02ab1691b5929237`