Skip to content

GitLab

Switch branch/tag
  1. 04 Nov, 2019 2 commits
  3. 03 Nov, 2019 1 commit
    • Zihao Ye's avatar
      [NN] nn modules & examples update (#890) · 9a0511c8
      Zihao Ye authored 
      * upd

* damn it

* fuck

* fuck pylint

* fudge

* remove some comments about MXNet

* upd

* upd

* damn it

* damn it

* fuck

* fuck

* upd

* upd

* pylint bastard

* upd

* upd

* upd

* upd

* upd

* upd

* upd

* upd

* upd
      9a0511c8
  5. 01 Nov, 2019 2 commits
    • xiang song(charlie.song)'s avatar
      [NN]Supporting TransR in app/kg score_func (#945) · 7f65199a
      xiang song(charlie.song) authored 
      * Add TransR for kge

* Now Pytorch TransR can run

* Add MXNet TransR

* Now mxnet can work with small dim size

* Add test

* Pass simple test_score

* Update test with transR score func

* Update RESCAL MXNet

* Add missing funcs

* Update init func for transR score

* Revert "Update init func for transR score"

This reverts commit 0798bb886095e7581f6675da5343376844ce45b9.

* Update score func of TransR MXNet

Make it more memory friendly and faster,
thourgh it is still very slow and memory consuming

* Update best config

* Fix ramdom seed for test

* Init score-func specific var

* Update Readme
      7f65199a
    • John Andrilla's avatar
      [doc] simple readability and style changes (#965) · a85382b0
      John Andrilla authored
      a85382b0
  7. 30 Oct, 2019 1 commit
    • xiang song(charlie.song)'s avatar
      [Bug Fix] Fix package reliability bug of networkx (#949) · 82499e60
      xiang song(charlie.song) authored 
      * upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* reproduce the bug

* Fix concurrency bug reported at #755.
Also make test_shared_mem_store.py more deterministic.

* Update test_shared_mem_store.py

* Update dmlc/core

* networkx >= 2.4 will break our examples

* Update tutorials/requirements

* fix selfloop edges

* upd version
      82499e60
  9. 29 Oct, 2019 2 commits
  11. 28 Oct, 2019 1 commit
  13. 26 Oct, 2019 1 commit
  15. 25 Oct, 2019 3 commits
  17. 21 Oct, 2019 7 commits
  19. 18 Oct, 2019 1 commit
  21. 12 Oct, 2019 1 commit
  23. 11 Oct, 2019 3 commits
    • xiang song(charlie.song)'s avatar
      Fix bug of KG train.py script. (#922) · 20439e1c
      xiang song(charlie.song) authored 
      It cannot work when only mxnet backend is installed.
      20439e1c
    • xiang song(charlie.song)'s avatar
      [KG] Update CI to cover Knowledge Graph (#913) · 93e3c49d
      xiang song(charlie.song) authored 
      * upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now t...
      93e3c49d
    • xiang song(charlie.song)'s avatar
      [KG] ComplEx score func for MXNet (#918) · bde75256
      xiang song(charlie.song) authored 
      * upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* reproduce the bug

* Fix concurrency bug reported at #755.
Also make test_shared_mem_store.py more deterministic.

* Update test_shared_mem_store.py

* Update dmlc/core

* Add complEx for mxnet

* ComplEx is ready for MXNet
      bde75256
  25. 09 Oct, 2019 2 commits
  27. 08 Oct, 2019 5 commits
    • Minjie Wang's avatar
      [Fix] Fix typo in KGE readme · 5eae8e05
      Minjie Wang authored
      5eae8e05
    • Quan (Andy) Gan's avatar
      [Doc] Fix hetero tutorial directory (#912) · 9d64927c
      Quan (Andy) Gan authored
      9d64927c
    • Quan (Andy) Gan's avatar
      minor docstring fix (#910) · a1cdc7a5
      Quan (Andy) Gan authored
      a1cdc7a5
    • Quan (Andy) Gan's avatar
      [Hetero][Tutorial] Heterograph tutorials (#878) · 3ee7e112
      Quan (Andy) Gan authored 
      * heterograph tutorial skeleton

* [WIP][Tutorial] Heterogeneous graph tutorial

* fix

* update
      3ee7e112
    • xiang song(charlie.song)'s avatar
      [Bug fix] Fix concurrency bug reported at issue#755 (#823) · fd1b1474
      xiang song(charlie.song) authored 
      * upd

* fig edgebatch edges

* add test

* trigger

* Update README.md for pytorch PinSage example.

Add noting that the PinSage model example under
example/pytorch/recommendation only work with Python 3.6+
as its dataset loader depends on stanfordnlp package
which work only with Python 3.6+.

* Provid a frame agnostic API to test nn modules on both CPU and CUDA side.

1. make dgl.nn.xxx frame agnostic
2. make test.backend include dgl.nn modules
3. modify test_edge_softmax of test/mxnet/test_nn.py and
    test/pytorch/test_nn.py work on both CPU and GPU

* Fix style

* Delete unused code

* Make agnostic test only related to tests/backend

1. clear all agnostic related code in dgl.nn
2. make test_graph_conv agnostic to cpu/gpu

* Fix code style

* fix

* doc

* Make all test code under tests.mxnet/pytorch.test_nn.py
work on both CPU and GPU.

* Fix syntex

* Remove rand

* Add TAGCN nn.module and example

* Now tagcn can run on CPU.

* Add unitest for TGConv

* Fix style

* For pubmed dataset, using --lr=0.005 can achieve better acc

* Fix style

* Fix some descriptions

* trigger

* Fix doc

* Add nn.TGConv and example

* Fix bug

* Update data in mxnet.tagcn test acc.

* Fix some comments and code

* delete useless code

* Fix namming

* Fix bug

* Fix bug

* Add test for mxnet TAGCov

* Add test code for mxnet TAGCov

* Update some docs

* Fix some code

* Update docs dgl.nn.mxnet

* Update weight init

* Fix

* reproduce the bug

* Fix concurrency bug reported at #755.
Also make test_shared_mem_store.py more deterministic.

* Update test_shared_mem_store.py

* Update dmlc/core
      fd1b1474
  29. 07 Oct, 2019 2 commits
  31. 06 Oct, 2019 4 commits
  33. 04 Oct, 2019 2 commits