Ptlflow

Major update to support Lightning 2 (finally!). However, it also introduces breaking changes from the previous v0.3 code. See the details below.

- Transitioning from v0.3 to v0.4: check the [v0.4 upgrade guide](https://ptlflow.readthedocs.io/en/latest/starting/v04_upgrade_guide.html)
- Added features:
- Support for YAML config files. See the [config file documentation](https://ptlflow.readthedocs.io/en/latest/starting/config_files.html)
- Table [comparing PTLFlow results with the original papers](https://ptlflow.readthedocs.io/en/latest/results/paper_ptlflow.html) to check the stability of the included models.
- Added new models:
- NeuFlow v2 https://arxiv.org/abs/2408.10161
- Add support for more datasets:
- Middlebury-ST [[https://vision.middlebury.edu/stereo/data/scenes2014/]{](https://vision.middlebury.edu/stereo/data/scenes2014/]%7B)[https://vision.middlebury.edu/stereo/data/scenes2014/}](https://vision.middlebury.edu/stereo/data/scenes2014/%7D)
- VIPER https://playing-for-benchmarks.org/

Added

- New models:
- MemFlow
- NeuFlow
- SEA-RAFT
- SplatFlow
- New datasets
- Kubric
- TartanAir
- ONNX and TensorRT conversion scripts to RAPIDFlow

Fixed

- LR scheduler when accumulating gradients

Added

- New models:
- CCMR
- LLA-Flow
- RAPIDFlow
- FP16 inference in most models
- Script to plot results

This is a major update and introduces breaking changes to v0.2.
The list of changes below is not comprehensive, there may be other changes that are not listed.

Added

- New models:
- DIP
- Flow1D
- FlowFormer++
- GMFlow+
- MatchFlow
- MS-RAFT+
- RPKNet
-SeparableFlow
- SKFlow
- VideoFlow
- New datasets:
- Middlebury
- Monkaa
- Spring
- Option to use RAFT's alt_cuda_corr for supported models
- Also added a pure PyTorch version of alt_cuda_corr, which is slower but does not need to be compiled

Fixed

- Compatibility with PyTorch 2.0, 2.1
- Compatibility issues with PyTorch Lightning 1.9
- Resizing augmentation when the valid mask is sparse
- Models should produce results more similar to the paper
- HOWEVER, we do not guarantee our results are correct. Use the official implementations for the most accurate results.

Changed

- Each model now handle its own IO reshaping, instead of using padding for all models
- speed_benchmark.py becomes model_benchmark.py and records more metrics
- Renamed model: pwcdcnet -> pwcnet, pwcnet -> pwcnet_nodc
- Updated requirements, support for many old versions are dropped
- Important requirements:
- python>=3.8,<3.12
- torch>=1.13,<2.2
- lightning>=1.9.0,<2

Fixed

- Memory leak in FlowMetrics caused when setting full_state_update=False

Added

- Support for AutoFlow dataset
- New models:
- CRAFT
- CSFlow
- FlowFormer
- GMFlow
- GMFlowNet

Fixed

- Compatibility issues with PyTorch Lightning 1.6