Welcome to fovi’s documentation!
fovi is a PyTorch library for implementing foveated vision. This library provides tools for foveated sampling and foveated neural network architectures.
Getting Started
fovi- Example notebooks
- Explore the foveated sensor manifold and basic concepts
- Learn how to do foveated sampling
- Build foveated CNNs from basic building blocks
- Build foveated ViTs and initialize a state-of-the-art foveated DINOv3 model:
- Learn how to extract intermediate activations from a model and explore the Trainer class
- Package boundaries and migration
- Versions and releases
Core Components
- fovi.sensing package
- fovi.arch package
- fovi.models package
- fovi.models.alexnet
- fovi.models.architectures
- fovi.models.convnextv2
- fovi.models.dinov3
- fovi.models.fovinet
- fovi.models.hub
- fovi.models.knnalexnet
- fovi.models.knnconvnextv2
- fovi.models.knnresnet
- fovi.models.knnvit
- fovi.models.loading
- fovi.models.pretrained_resnet
- fovi.models.probes
- fovi.models.resnet
- fovi.models.vit
- fovi.training package
Utilities & Tools
- fovi.utils package
add_to_all()get_random_name()get_model()reproducible_results()HiddenPrintsnormalize()timeit()load_pretrained()analyze_rf()normalize_imagenet()flatten_dict()unflatten_dict()- fovi.utils.fastaugs package
- fovi.utils.backup
- fovi.utils.flops
- fovi.utils.image
- fovi.utils.knnprobe
- fovi.utils.lora
- fovi.utils.losses
- fovi.utils.lr_scheduling
- fovi.utils.std_transforms
- fovi.demo
- fovi.paths
- fovi.trainer
- fovi.visualizer