Perceiver-io

This release adds a Perceiver IO for predicting the optical flow between two images. It also adds utilities for producing an optical flow video from an input video (see [inference notebook](https://t.co/hJMSM9qNBm), for a demo). Thanks to cstub for this great contribution. See [milestone 0.7.0](https://github.com/krasserm/perceiver-io/milestone/3?closed=1) for a list of closed tickets.

Data preprocessing and documentation enhancements, major refactorings

Functional enhancements:

- Support for static word masking in addition to dynamic word masking.
- Support for individual token masking in addition to whole word masking.
- Task-specific data preprocessing for all supported text datasets.
- Constant learning rate scheduler with warmup now used by default.

Documentation enhancements:

- All training examples now provided as command line and Python script.
- Better overview of official models and example training checkpoints.
- Example training checkpoints can now be downloaded individually.
- Minor enhancements to all other documentation sections.

Refactorings and breaking changes:

- Rename `image` package to `vision`.
- `TextDataModule` base class now implements complete preprocessing logic.
- `TextDataModule` subclasses only convert source dataset to a common structure.
- Abstraction over cross-attention query creation (`QueryProvider`).
- Decouple `OutputAdapter` interface from trainable cross-attention query.
- Implement learned positions encodings as `nn.Embedding`.
- Move adapters to separate `perceiver.model.core.adapter` module.
- Rename `PerceiverConfig` to `PerceiverIOConfig`
- Rename `LitModel` base class to `LitPerceiverIO`.
- `LitClassifier.forward` now behaves like the wrapped model's `forward`.
- Object-oriented design of conversion from Hugging Face Perceiver models.
- Major refactoring of `PerceiverAR` and `CausalLanguageModel`.
- Move `FourierPositionEncoding` to perceiver.model.core.position` module.

Implementation of [Perceiver AR](https://arxiv.org/abs/2202.07765) including training and inference examples (#20).

- Upgrade to PyTorch Lightning 1.7.3 and PyTorch 1.12.1.
- See [milestone 0.5.1](https://github.com/krasserm/perceiver-io/milestone/1?closed=1) for a complete list of closed tickets.

Highlights of the [0.5.0](https://github.com/krasserm/perceiver-io/tree/0.5.0) release:

- Import [pretrained models](https://github.com/krasserm/perceiver-io#pretrained-models) from Huggingface Hub
- New [training examples](https://github.com/krasserm/perceiver-io#training-examples)
- New [inference examples](https://github.com/krasserm/perceiver-io/blob/main/notebooks/inference_examples.ipynb) [](https://colab.research.google.com/github/krasserm/perceiver-io/blob/0.5.0/notebooks/inference_examples.ipynb)
- UTF-8 bytes tokenization