Skip to content

GitLab

Switch branch/tag
  1. 08 Oct, 2022 1 commit
  3. 19 Sep, 2022 1 commit
  5. 07 Sep, 2022 1 commit
    • ndickson-nvidia's avatar
      [Feature] Added exclude_self and output_batch to knn graph construction... · 684f66b7
      ndickson-nvidia authored 
      
[Feature] Added exclude_self and output_batch to knn graph construction (Issues #4323 #4316) (#4389)

* * Added "exclude_self" and "output_batch" options to knn_graph and segmented_knn_graph
* Updated out-of-date comments on remove_edges and remove_self_loop, since they now preserve batch information

* * Changed defaults on new knn_graph and segmented_knn_graph function parameters, for compatibility; pytorch/test_geometry.py was failing

* * Added test to ensure dgl.remove_self_loop function correctly updates batch information

* * Added new knn_graph and segmented_knn_graph parameters to dgl.nn.KNNGraph and dgl.nn.SegmentedKNNGraph

* * Formatting

* * Oops, I missed the one in segmented_knn_graph when I fixed the similar thing in knn_graph

* * Fixed edge case handling when invalid k specified, since it still needs to be handled consistently for tests to pass
* Fixed context of batch info, since it must match the context of the input position data for remove_self_loop to succeed

* * Fixed batch info resulting from knn_graph when output_batch is true, for case of 3D input tensor, representing multiple segments

* * Added testing of new exclude_self and output_batch parameters on knn_graph and segmented_knn_graph, and their wrappers, KNNGraph and SegmentedKNNGraph, into the test_knn_cuda test

* * Added doc comments for new parameters

* * Added correct handling for uncommon case of k or more coincident points when excluding self edges in knn_graph and segmented_knn_graph
* Added test cases for more than k coincident points

* * Updated doc comments for output_batch parameters for clarity

* * Linter formatting fixes

* * Extracted out common function for test_knn_cpu and test_knn_cuda, to add the new test cases to test_knn_cpu

* * Rewording in doc comments

* * Removed output_batch parameter from knn_graph and segmented_knn_graph, in favour of always setting the batch information, except in knn_graph if x is a 2D tensor
Co-authored-by: default avatarMinjie Wang <wmjlyjemaine@gmail.com>
      684f66b7
  7. 05 Sep, 2022 2 commits
  9. 31 Aug, 2022 1 commit
  11. 15 Aug, 2022 1 commit
  13. 09 Aug, 2022 1 commit
  15. 01 Aug, 2022 1 commit
  17. 29 Jul, 2022 1 commit
    • Xin Yao's avatar
      [Feature] Add CUDA Weighted Neighborhood Sampling (#4064) · 86c81b4e
      Xin Yao authored 
      

* add weighted sampling without replacement (A-Chao)

* improve Algorithm A-Chao with block-wise prefix sum

* correctly fill out_idxs

* implement weighted sampling with replacement

* small fix

* merge host-side code of weighted/uniform sampling

* enable unit tests for cuda weighted sampling

* move thrust/cub wrapper to the cmake file

* update docs accordingly

* fix linting

* fix linting

* fix unit test

* Bump external CUB/Thrust versions

* Fix code style and update description of algorithm design

* [Feature] GPU support weighted graph neighbor sampling
commit by pengqirong(OPPO)

* merge pengqirong's implementation

* revert the change to cub and thrust

* fix linting

* use DeviceSegmentedSort for better performance

* add more comments

* add necessary notes

* add necessary notes

* resolve some comments

* define THRUST_CUB_WRAPPED_NAMESPACE

* fix doc
Co-authored-by: default avatar彭齐荣 <657017034@qq.com>
      86c81b4e
  19. 27 Jul, 2022 1 commit
  21. 26 Jul, 2022 1 commit
  23. 14 Jul, 2022 1 commit
  25. 01 Jul, 2022 2 commits
  27. 30 Jun, 2022 2 commits
  29. 29 Jun, 2022 2 commits
  31. 28 Jun, 2022 1 commit
  33. 23 Jun, 2022 1 commit
  35. 14 Jun, 2022 1 commit
  37. 12 Jun, 2022 1 commit
  39. 07 Jun, 2022 1 commit
  41. 02 Jun, 2022 2 commits
  43. 28 May, 2022 1 commit
  45. 25 May, 2022 1 commit
  47. 24 May, 2022 1 commit
  49. 23 May, 2022 1 commit
  51. 17 May, 2022 1 commit
    • ndickson-nvidia's avatar
      [Feature] Added floating-point conversion functions to dgl.transforms.functional (#3890) · e0e8736f
      ndickson-nvidia authored 
      

* * Added half_(), float_(), and double_() functions to DGLHeteroGraph, HeteroNodeDataView, and HeteroEdgeDataView, for converting floating-point tensor data to float16, float32, or float64 precision

* * Extracted out private functions for floating-point type conversion, to reduce code duplication

* * Added test for floating-point data conversion functions, half_(), float_(), and double_()

* * Moved half_(), float_(), and double_() functions from HeteroNodeDataView and HeteroEdgeDataView to Frame class

* * Updated test_float_cast() to use dgl.heterograph instead of dgl.graph

* Added to CONTRIBUTORS.md

* * Changed data type conversion to be deferred until the data is accessed, to avoid redundant conversions of data that isn't used.

* * Addressed issues flagged by linter

* * Worked around a bug in the old version of mxnet that's currently used for DGL testing

* * Only defer Column data type conversion if there is a pending device transfer or index sampling to be done.  This is expected to be the desired behaviour based on discussions of a few use cases, as described in the comments.

* * Moved floating-point feature data conversion functions to dgl.transforms.functional
* Changed them from in-place behaviour to shallow copy (out-of-place) behaviour

* * Fixed linter issues

* * Removed lines that unintentionally added to_half, to_float, and to_double to DGLHeteroGraph
* Moved _init_api line to the end of the file again

* * Removed one of the two leading underscores from Frame.__astype_float, making it not fully private
Co-authored-by: default avatarnv-dlasalle <63612878+nv-dlasalle@users.noreply.github.com>
      e0e8736f
  53. 16 May, 2022 3 commits
  55. 07 May, 2022 1 commit
  57. 23 Apr, 2022 1 commit
  59. 12 Apr, 2022 2 commits
  61. 11 Apr, 2022 1 commit
  63. 09 Apr, 2022 1 commit