Module tch::vision

The vision module groups functions and models related to computer vision.

Modules

• alexnet
  AlexNet. https://arxiv.org/abs/1404.5997
• cifar
  The CIFAR-10 dataset.
• convmixer
  ConvMixer implementation.
• dataset
  A simple dataset structure shared by various computer vision datasets.
• densenet
  DenseNet implementation.
• dinov2
  DINOv2: Learning Robust Visual Features without Supervision https://github.com/facebookresearch/dinov2 The weights can be extracted from pre-trained Python models using python src/vision/export_dinov2.py.
• efficientnet
  EfficientNet implementation.
• image
  Utility functions to manipulate images.
• imagenet
  Helper functions for ImageNet like datasets.
• inception
  InceptionV3.
• mnist
  The MNIST hand-written digit dataset.
• mobilenet
  MobileNet V2 implementation. https://ai.googleblog.com/2018/04/mobilenetv2-next-generation-of-on.htmla
• resnet
  ResNet implementation.
• squeezenet
  SqueezeNet implementation.
• vgg
  VGG models.