- Notifications
You must be signed in to change notification settings - Fork0
Datasets, Transforms and Models specific to Computer Vision
License
zxd1997066/vision
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
The torchvision package consists of popular datasets, model architectures, and common image transformations for computervision.
Please refer to theofficialinstructions to install the stableversions oftorch andtorchvision on your system.
To build source, refer to ourcontributingpage.
The following is the correspondingtorchvision versions and supported Pythonversions.
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 |
Torchvision currently supports the following image backends:
- torch tensors
- PIL images:
- Pillow
- Pillow-SIMD - amuch faster drop-in replacement for Pillow with SIMD.
Read more in in ourdocs.
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 anyconflicting version of ffmpeg installed. Currently, this is only supported on Linux.
conda install -c conda-forge 'ffmpeg<4.3'python setup.py installRefer toexample/cpp.
DISCLAIMER: thelibtorchvision library includes the torchvisioncustom ops as well as most of the C++ torchvision APIs. Those APIs do not comewith any backward-compatibility guarantees and may change from one version tothe next. Only the Python APIs are stable and with backward-compatibilityguarantees. So, if you need stability within a C++ environment, your best bet isto export the Python APIs via torchscript.
You can find the API documentation on the pytorch website:https://pytorch.org/vision/stable/index.html
See theCONTRIBUTING file for how to help out.
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 todetermine 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 datasetto be included in this library, please get in touch through a GitHub issue. Thanks for your contribution to the MLcommunity!
The pre-trained models provided in this library may have their own licenses or terms and conditions derived from thedataset used for training. It is your responsibility to determine whether you have permission to use the models for youruse case.
More specifically, SWAG models are released under the CC-BY-NC 4.0 license. SeeSWAG LICENSE for additional details.
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}}}