929742b588
[Feature] Reimplement Immutable graph index in DGL ( #342 )
...
* init.
* it's compiled.
* add immutable graph constructor.
* add immutable graph API.
* fix.
* impl get adjacency matrix.
* fix.
* fix graph_index from scipy matrix.
* add neighbor sampling.
* remap vertex ids.
* fix.
* move sampler test.
* fix tests.
* add comments
* remove mxnet-specific immutable graph.
* fix.
* fix lint.
* fix.
* try to fix windows compile error.
* fix.
* fix.
* add test.
* unify Graph and ImmutableGraph.
* fix bugs.
* fix compile.
* move immutable graph.
* fix.
* remove print.
* fix lint.
* fix
* fix lint.
* fix lint.
* fix test.
* fix comments.
* merge GraphIndex and ImmutableGraphIndex.
* temp fix.
* impl GetAdj.
* fix lint
* fix.
* fix.
* fix.
* fix.
* fix.
* use csr only for readonly graph.
* Revert "use csr only for readonly graph."
This reverts commit 8e24bb033af8504531b22849de5b7567b168e0d5.
* remove code.
* fix.
* fix.
* fix.
* fix.
* fix.
* fix.
* address comments.
* fix for comments.
* fix comments.
* revert.
* move test_graph_index to compute.
* fix.
* fix.
* impl GetAdj for coo.
* fix.
* fix tests.
* address comments.
* address comments.
* fix comment.
* address comments.
* use lambda.
* other comments.
* address comments.
* modify the semantics of edges.
* fix order.
* use DGLIdIter
* fix.
* remove NotImplemented.
* revert some code.
2019-01-17 09:59:53 +08:00
e19cd62ecd
[Test] Unify tests for different backends ( #333 )
...
* test basics
* batched graph & filter, mxnet filter fix
* frame and function; bugfix
* test graph adj and inc matrices
* fixing start = 0 for mxnet
* test index
* inplace update & line graph
* multi send recv
* more tests
* oops
* more tests
* removing old test files; readonly graphs for mxnet still kept
* modifying test scripts
* adding a placeholder for pytorch to reserve directory
* torch 0.4.1 compat fixes
* moving backend out of compute to avoid nose detection
* tests guide
* mx sparse-to-dense/sparse-to-numpy is buggy
* oops
* contribution guide for unit tests
* printing incmat
* printing dlpack
* small push
* typo
* fixing duplicate entries that causes undefined behavior
* move equal comparison to backend
2019-01-05 23:32:33 -05:00
2664ed2dff
[Bugfix] Fix multiple send recv ( #320 )
...
* fix bug: frame append should check itself
* more test case
* fix multi-send-recv bug
* remv msg graph and clean up
* test cases
* more test case
* fix for batchedgraph
* fix bugs: converting from a graph with edges
* fix
* add more operators to utils.Index
* clear frame executor
* change message indicator to a graph level index
* fix test cases
* guard the case that mxnet does not support concat zero shape tensor
* fix bug: avoid convert full slice to numpy
* test multi-send-recv after conversion
* fix as request (partially)
* add dtype, ctx to full_1d
* add slice data to utils.Index
* fix
* more doc string
* fix as requested
2018-12-23 21:35:49 -05:00
899d125bb1
Add tests for MXNet and throw NotImplementedError if not implemented ( #258 )
...
* add more unit tests for mxnet.
* fix.
2018-12-05 10:41:33 -08:00
eafcb7e7f5
[Bugfix][MXNet] Fix edge order and builtin max bug in mx ( #247 )
...
* Fix edge order and builtin max bug in mx
* fix as requested
2018-12-05 01:32:54 -08:00
a5a35d1f7a
[Sampler] improve random shuffle performance in sampler ( #228 )
...
* fix.
* make it generic.
* add the API.
* fix.
* remove mxnet.
2018-12-04 09:24:32 -08:00
5f89cd662e
Fix the convergence problem in SSE. ( #162 )
...
* add a test.
* move file.
* debug
* add degree normalization.
* it can converge now.
* remove hidden_data.
* use readonly graph index.
* use subgraph loader.
* refactor code and remove intermediate data.
* split inference.
* mix cpu and gpu training.
* fix mxnet sparse_matrix constructor.
* convert tensor context.
* set up the prediction model.
* load mxnet csr directly.
* add timing.
* move test_sse.py to sse_batch.py
* fix the tensor version of SSE.
* update README.
2018-11-20 15:57:52 +08:00
048f6d7a30
[GraphIndex] refactor graph caching ( #150 )
...
* refactor graph caching
* fix mx test
* fix typo
2018-11-13 22:12:38 -05:00
40ca5de450
[API] Readout interfaces ( #124 )
...
* fixing builtin src*edge shape mismatch
* bundled function refactor (?)
* fixing names
* readout prototype
* oops
* more fixes
* removing readout prototype
* sum_on() with SPMV, fixing batching with 0 edges
* readouts with segmented sum
* typo (??????)
* fixes NLTK dependency (#125 )
* misc fixes including #126 (pushing again)
* sanity check for mxnet
* fixes NLTK dependency (#125 ) and #126
* reverting to sum_nodes/edges
2018-11-10 11:35:34 -05:00
bd0e4fa0b3
[MXNet][API] move to the new API ( #123 )
...
* move gat to the new api.
* fix gcn.
* update sse.
* fix dgl core.
* update sse.
* fix small bugs in dgl core.
* fix mxnet tests.
* retrigger
* address comments and fix more bugs.
* fix
* fix tests.
2018-11-08 10:00:47 -08:00
7241a9c008
[Backend] backend interface ( #109 )
...
* backend interface
* small fix
* more comments to the data type dict
* WIP
* convert_to and narrow
* WIP
* pytorch and numpy backend; WIP on mxnet backend
* mxnet backend
* narrow
* Fix all usages
* fix for mx
* fix for mx
* fix mx
* fix mx
* fix mx
* fix mx
* fix mx
* fix mx
* fix mx
* revert jenkins
* add sparse_matrix api
* sparse matrix api
* some fixme
* Fix as requested
2018-11-04 21:42:39 -05:00
Da Zheng