* multi-process version of transformer
* lots of fix
* fix bugs and accum gradients for multiple batches
* many fixes
* minor
* upd
* set torch device
* fix bugs
* fix and minor
* comments and clean up
* uncomment viz code
* fix gat residual bug
* fix the residual addition; output heads; add some shape notations;
* minor
* fix the output head average
* add requests package in requirement
* add cache to adj and incmat
* Fix bug in cached adj/inc
* mx gcn spmv runnable; acc debugging...
* fix bug in mx gcn that loss is not correctly calculated
* fix mx utest
* fix as requested
* use raw parameter tensors rather than dense layer
* fix dropout
* Add numbers in readme
* data preprocessing for rgcn
* edge subgraph
* WIP: RGCN
* use edge feature in spmv
* fix bugs
* match AIFB accuracy
* match mutag accuracy
* avoid materializing in featureless case
* remove untouched nodes and relabel nodes
* fix python list concatenate overhead
* sparsely store edge types
* refactor entity classify code for clean link prediction implementation
* further refactor code
* refactoring
* rgcn block decompose layers
* link predict dataset
* link predict model and eval code
* dropout, self-loop, regularization, etc, plus bug fixes
* update to new api
* dataset update
* bugs, WIP, need to impl early stopping and filtered metrics
* instruction to run, and minor
* group conv and early stop
* clean slow code
* some code comments
* use new api in model code
* change data preprocessing
* entity classify model
* WIP
* move dgl graph out of model
* hot fix for extract zip
* fix link predict model
* use latest dgl apis
* still have memory issue...
* bug fix and move inference to cpu
* move rgcn data processing to contrib
* th.allclose -> U.allclose
* minor change in readme
* fix memory issue in entity classify
* fix and testing code for link predict
* fix entity classify
* clean up
* fix comments
* revert erroneous git merge changes
* code clean up and more comments
* minor
* dependent package version
* lazy eval edge ids.
* parallelize node id lookup.
* fix a bug.
* use mxnet for index.
* use update_all in the subgraph training.
* sample neighbors.
* Revert "parallelize node id lookup."
This reverts commit e661f69bb06cb5a7c246f0e106f245e27800e220.
* update README.
* cache subgraphs.
* support all degrees.
* cache adj in CPU.
* fix a bug in sse.
* print.
* raise error on mutable graphs.
* measure train time per epoch.
* fix a bug in graph_index.
* remove readonly in DGLSubGraph.
* cache subgraph properly.
* accelerate getting adjacency.
* split infer.
* lazy eval edges.
* specify inference mode.
* update for new sampler.
* use new mxnet sampling api.
* fix indent.
* remove profiling code.
* remove mxnet from sampler.
* return a lambda function for graph edges.
* add docs for immutable subgraph.
* Revert "return a lambda function for graph edges."
This reverts commit 0de5d7f100e230c518a3fb8976a6227f474d09ee.
* get parent_eid.
* cherry picking optimization from jtnn
* adding official code. TODO: fix DGLMolTree
* updating to current api. vae test still failing
* reverting to list stacking
* reverting to list stacking
* cleaning x flags (stupid windows)
* cleaning x flags (stupid windows)
* adding stats
* optimization
* updating dgl stats
* update again
* more optimization
* looks like computation is faster
* removing profiling code
* cleaning obsolete code
* remove comparison warning
* readme update
* official implementation got a lot faster
* minor fixes
* unbatch by slicing frames
* working around unbatch
* reduce pack
* oops
* support frame read/write with slices
* reverting back to readout as unbatch-by-slicing slows down backward
* reverting to unbatch by splitting; slicing is unfriendly to backward
* replacing lru cache with static object factory
* cherry picking optimization from jtnn
* unbatch by slicing frames
* reduce pack
* oops
* support frame read/write with slices
* reverting to unbatch by splitting; slicing is unfriendly to backward
* replacing lru cache with static object factory
* replacing Scheme object with namedtuple
* forgot the find edges interface
* subclassing namedtuple
* updating to the latest api spec
* bugfix
* bfs with edges
* dfs toy test case
* clean up
* style fix
* bugfix
* update to latest api; include traversal
* replacing with readout
* simplify decoder
* oops
* cleanup
* reducing number of sets
* more speed up
* profile results
* random fixes
* fixing tvmarray handling incontiguous dlpack input
* fancier dataloader
* fix a potential context mismatch
* todo: support pickling or using scipy in multiprocessing load
* pickling support
* resorting to suggested way of pickling
* custom attribute pickling check
* working around a weird pytorch pickling bug
* including partial frame case
* enabling multiprocessing dataloader
* pickling everything now
* really works
* oops
* updated profiling results
* cleanup
* fix as requested
* cleaning random blank lines
* removing profiler outputs
* starting decoding
* testing, WIP
* tree decoding
* graph decoding, WIP
* graph decoding works
* oops
* fixing legacy apis
* trimming number of candidate structures
* sampling cleanups
* removing comparison test
* updated description
Minjie Wang