Pytorch Cluster Versions Save

PyTorch Extension Library of Optimized Graph Cluster Algorithms

1.6.3

7 months ago

Fix backward compatibility issue with PyTorch < 1.12
Remove torch.jit.script conversion of functions on module import

1.6.2

7 months ago

What's Changed

Add batch_size argument for fps, knn, radius functions (https://github.com/rusty1s/pytorch_cluster/pull/175)
Extend FPS with an extra ptr argument https://github.com/rusty1s/pytorch_cluster/pull/180)
Add PyTorch 2.1.0 support (https://github.com/rusty1s/pytorch_cluster/pull/191)

New Contributors

@piotrchmiel made their first contribution in https://github.com/rusty1s/pytorch_cluster/pull/175
@cimadure made their first contribution in https://github.com/rusty1s/pytorch_cluster/pull/179
@dsciebu made their first contribution in https://github.com/rusty1s/pytorch_cluster/pull/180
@AgarwalSaurav made their first contribution in https://github.com/rusty1s/pytorch_cluster/pull/188

Full Changelog: https://github.com/rusty1s/pytorch_cluster/compare/1.6.1...1.6.2

1.6.1

1 year ago

Added support for PyTorch 2.0
Added support for return the indices of sampled edges in random_walk (#139)
Added bf16 support for knn, radius and graclus (#144)
Add safety checks on batch layout in nearest (#168)

1.6.0

2 years ago

Improve calculation of num_nodes in random_walk (in case num_nodes=None) (#112)
Fix knn/radius calculation for batches with zero-point examples
Heavily improved efficiency of knn/radius calculation
Half-precision support (#119)

1.5.9

3 years ago

Reduced the size of shared library files
CUDA wheels can now also operate on CPU-only devices
Added parallelization strategies for CPU functionalities
fps can now take in different ratios across different batched point sets, i.e. ratio can now be a torch.Tensor
Fixed a bug in which radius computed slightly different results across CPU and CUDA versions

1.5.8

3 years ago

PyTorch 1.7 wheels
random_walk now supports q != 1 and p != 1 via rejection sampling

1.5.7

3 years ago

PyTorch 1.6.0 wheels
Fixed a bug in radius where the max_num_neighbors argument has been ignored

1.5.6

3 years ago

This release fixes some issues in the new knn and radius CPU implementations that have led to memory leaks. It is strongly recommended to update the package in case you are currently using torch-cluster==1.5.5.

1.5.5

3 years ago

torch-cluster is now fully-jittable thanks to new implementations for knn and radius based on nanoflann rather than scipy.

1.5.4

4 years ago

Fixed a bug in the CUDA version of fps.