torchvision 0.2.1

torchvision contains a variety of Datasets, Transforms and Models specific to Computer Vision.

The application consists of:

  • vision.datasets : Data loaders for popular vision datasets
  • vision.models : Definitions for popular model architectures, such as AlexNet, VGG, and ResNet and pre-trained models.
  • vision.transforms : Common image transformations such as random crop, rotations etc.
  • vision.utils : Useful stuff such as saving tensor (3 x H x W) as image to disk, given a mini-batch creating a grid of images, etc.

Accessing the software

To load the module, issue the following command:

$ module load torchvision/0.2.1-foss-2018a-Python-3.6.3-CUDA-9.0.176

torchvision is a Python package. It needs to be imported into your Python script to be used:

import torchvision

<torchvision commands>

Accessing Previous Versions

Wherever possible, previous versions of this application will be retained for continuity, especially for research projects that require a consistent version of the software throughout the project. Such versions, however, may be unsupported by IT Services or the applications vendor, and may be withdrawn at short or no notice if they can no longer run on the cluster - for example, essential operating system upgrades may be incompatible with old versions.

Previous versions of this application are recorded below:

Known Problems & Limitations

None.

Other Information

The Support Level for this application is An.

Visit the torchvision Github repository for more information regarding this application.


Last modified: 31 May 2018


Colleges

Professional Services