Commit Graph

381 Commits (e88325640042796274d88f0596abcff4dba285e8)

Author SHA1 Message Date
raver119 10d6c3b024
do not relocate stuff on java side (#444)
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
2020-05-09 12:56:45 +03:00
raver119 2849299bfb
Fix for https://github.com/eclipse/deeplearning4j/issues/8909 (#430)
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
2020-05-09 08:09:26 +03:00
raver119 0613485654
compression ops (#436)
* Added declarations for decode/encode_bitmap ops.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added implementation for bitmap encoding/decoding ops.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added helpers for encode/decode bitmap ops.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored encodingBitmap helper.

Signed-off-by: shugeo <sgazeos@gmail.com>

* threshold encode/decode skeleton

* helper skeleton

* minor import fix

* encoder shape fn & op impl

* thresholdEncode cpu impl

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* thresholdDecode cpu impl

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* Only cosmetical changes.

Signed-off-by: shugeo <sgazeos@gmail.com>

* placeholder

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* Added cuda implementation for bitmap decode helper.

Signed-off-by: shugeo <sgazeos@gmail.com>

* cuda thresholdEstimate

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* cuda thresholdDecode

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* next step

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* - nano cmakelist update (get rid of Clion section)
- fixed forgotten throw in AtomicTests

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* thesholdEncode cuda impl

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* Added tests for bitmap encoding/decoding ops.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed tests for encode/decode bitmaps.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored decode/encode helpers.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed crashes with bitmap decode/encode helpers.

Signed-off-by: shugeo <sgazeos@gmail.com>

* bitmap encode/decode CPU

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* bitmap encode/decode CUDA

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* C API removed for threshold/bitmap encode

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* EncodeBitmap/DecodeBitmap Java side

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* EncodeThreshold/DecodeThreshold Java side

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* EncodeThreshold/DecodeThreshold Java side

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* few more tests for threshold encoding

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* minor test tweak

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* two special tests

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* encodeBitmap CPU fix

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* parallel_long/parallel_double proper spans fix

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* encodeThreshold CUDA fix

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* nano fix

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* grid tweaks

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* RTX adaptation for thresholdEncode

Signed-off-by: raver119 <raver119@gmail.com>

* don't allow threshold encoding for length < 2

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* get rid of NDArrayCompressor in EncodingHandler

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* one more minor update of EncodingHandler

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* one more minor tweak of EncodingHandler

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* - matmul allows integer data types use
- EncodingHandler boundary default value
- few tests for integer matmul

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* minor fix of CUDA bitmap encode

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* boundary changed to integer everywhere

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* boundary changed to integer everywhere

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* re-enable CUDA deallocator

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* threshold encoder fix for systems without omp

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* - encode_threshold now requires non-negative boundary
- minor tweak in EncodingHandler

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* restore parallelism in decode_bitmap

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* fall back to omp for encode_bitmap cpu

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* single time casts

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* - additional test for encode_threshold
- sync buffers to device before calling for shape function

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

Co-authored-by: shugeo <sgazeos@gmail.com>
2020-05-08 20:59:39 +03:00
Alex Black 615a48f0cf
Fixes (#434)
* #8901 Avoid unnecessary warning in SameDiffLoss

Signed-off-by: Alex Black <blacka101@gmail.com>

* Improved error messages for conv2d layers - NCHW vs. NHWC

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-05-05 12:24:03 +10:00
Alex Black b70e02a915
Fix deeplearning4j-util dependency + update remnants still using it (#428)
Signed-off-by: Alex Black <blacka101@gmail.com>
2020-05-04 15:54:03 +10:00
raver119@gmail.com 6c9a14d8c2 added missing copyright :)
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
2020-05-01 22:22:34 +03:00
raver119@gmail.com c1e4613dba rootDir null validation in ExistingMiniBatchDataSetIterator
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
2020-05-01 22:11:56 +03:00
raver119@gmail.com a6ca87dce6 one deprecated method
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
2020-04-30 11:22:25 +03:00
Alex Black ffab4eec42
Fix SameDiff session termination condition when listener requests array after final requested output (#423)
* custom listener test

* abst session

Signed-off-by: eraly <susan.eraly@gmail.com>

* Partial fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix for execution termination condition

Signed-off-by: Alex Black <blacka101@gmail.com>

* Small error mesage improvement

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: eraly <susan.eraly@gmail.com>
2020-04-30 10:47:32 +10:00
Alex Black 88d3c4867f
Refactor packages to fix split package issues (#411)
* Refactor nd4j-common: org.nd4j.* -> org.nd4j.common.*

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix CUDA (missed nd4j-common package refactoring changes)

Signed-off-by: Alex Black <blacka101@gmail.com>

* nd4j-kryo: org.nd4j -> org.nd4j.kryo

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix nd4j-common for deeplearning4j-cuda

Signed-off-by: Alex Black <blacka101@gmail.com>

* nd4j-grppc-client: org.nd4j.graph -> org.nd4j.remote.grpc

Signed-off-by: Alex Black <blacka101@gmail.com>

* deeplearning4j-common: org.deeplearning4.* -> org.deeplearning4j.common.*

Signed-off-by: Alex Black <blacka101@gmail.com>

* deeplearning4j-core: org.deeplearning4j.* -> org.deeplearning.core.*

Signed-off-by: Alex Black <blacka101@gmail.com>

* deeplearning4j-cuda: org.deeplearning4j.nn.layers.* -> org.deeplearning4j.cuda.*

Signed-off-by: Alex Black <blacka101@gmail.com>

* Import fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* deeplearning4j-nlp-*: org.deeplearning4.text.* -> org.deeplearning4j.nlp.(language).*

Signed-off-by: Alex Black <blacka101@gmail.com>

* deeplearning4j-ui-model: org.deeplearning4j.ui -> org.deeplearning4j.ui.model

Signed-off-by: Alex Black <blacka101@gmail.com>

* datavec-spark-inference-{server/model/client}: org.datavec.spark.transform -> org.datavec.spark.inference.{server/model/client}

Signed-off-by: Alex Black <blacka101@gmail.com>

* datavec-jdbc: org.datavec.api -> org.datavec.jdbc

Signed-off-by: Alex Black <blacka101@gmail.com>

* Delete org.deeplearning4j.datasets.iterator.impl.MultiDataSetIteratorAdapter in favor of (essentially identical) org.nd4j.linalg.dataset.adapter.MultiDataSetIteratorAdapter

Signed-off-by: Alex Black <blacka101@gmail.com>

* ND4S fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* nd4j-common-tests: org.nd4j.* -> org.nd4j.common.tests

Signed-off-by: Alex Black <blacka101@gmail.com>

* Trigger CI

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8878 Ignore CUDA tests on modules with 'nd4j-native under cuda' issue

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix bad imports in tests

Signed-off-by: Alex Black <blacka101@gmail.com>

* Add ignore on test (already failing) due to #8882

Signed-off-by: Alex Black <blacka101@gmail.com>

* Import fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Additional import fixes

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-29 11:19:26 +10:00
raver119 bc8a9d1996
allocation of buffers backed by workspaces with 1 method call instead of 3 now (#420)
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
2020-04-28 20:38:16 +03:00
Alex Black 3c28caa52a
Add ResourceUtils.listClassPathFiles (#416)
Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-26 18:32:49 +10:00
Alex Black 83f88a1b0d
[WIP] Add test: "all ops in namespace" scanner/check (#413)
* #8879 'All ops in namespace' scanner first steps

Signed-off-by: Alex Black <blacka101@gmail.com>

* Clean up and polish op mapping check utility

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-26 12:27:11 +10:00
Alex Black 9e7395667f
MKLDNNConvHelper: don't permute; pass in weight format arg (#412)
* MKLDNNConvHelper: don't permute; pass in weight format arg

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix flaky tests unrelated to main branch change

Signed-off-by: Alex Black <blacka101@gmail.com>

* Don't log every extracted file for LFW and other auto-downloaded image loaders using BaseImageLoader.downloadAndUntar

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-26 01:04:31 +10:00
Andrii T 58b11bfecc
Map C++ ops to Java (#392)
* MergeMaxIndex, ReverseBp, Tri, Triu and TriuBp added

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Upsamling3d draft

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* minor fix (upsampling3dBp inputDatatype.size=2)

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* polished testcases

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* matching of Upsampling3d input format according to cpp iArg

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* ops generated from codegen

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* requested changes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* added super() for Triu

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* everything passes except TriuOp

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Tri op dtype arg (output datatype config support) + default float32

Signed-off-by: Alex Black <blacka101@gmail.com>

* Small fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* temporary commit with manually edited sd/nd ops

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Cannot use 'val' here because initializer expression does not have a representable type: Type cannot be resolved

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* all tests passed

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* few requested changes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Small fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Ignore reverse_bp test due to logged issue

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix reverse op

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix MergeMaxIndex dtype -> iarg

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-25 23:56:02 +10:00
Andrii T bd376ca993
GRU and GRUBp (#410)
* GRU and GRUBp ops added and tested

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* minor polishing

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* few requested changes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* regenerated namespace + small fix in RnnOpValidation

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Fix bad character in RnnOpValidation

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-25 01:12:46 +10:00
raver119 5e779574cb
Few Workspace tweaks (#409)
* Allow to destroy workspaces on demand

Signed-off-by: raver119 <raver119@gmail.com>

* MMAP'd workspace can't have LearningPolicy

Signed-off-by: raver119 <raver119@gmail.com>

* throw an exception on CUDA

Signed-off-by: raver119 <raver119@gmail.com>
2020-04-23 15:50:30 +03:00
Alex Black f5f77df846
Dependency version upgrades + small SameDiff fix (#405)
* #8861 Training evaluation on variables not required for loss fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* Dependency version updates flagged by dependabot

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-23 15:38:42 +10:00
raver119 8f765c80ff
- do not use GetShortName approach for mmap on windows (#408)
- additional test for long file names on windows

Signed-off-by: raver119 <raver119@gmail.com>
2020-04-23 08:24:49 +03:00
Alex Black 75cc6e2ed7
Increase default timeouts [WIP] (#407)
* Increase default test timeout to 60 sec due to slow PPC CI machines

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix flaky NLP test (randomly fails due to no RNG seed set)

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-23 10:46:42 +10:00
Alex Black 3c6cb6d1a3
#8503 Add timeouts for downloads (test resources, Downloader utility) (#406)
Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-23 08:39:13 +10:00
Alexander Stoyakin ccb216a3ed
Fixing issues from Sonar report (#391)
* Fixing issues from Sonar report

* Proper logger of exceptions

* Coding style fixes

* Use dup parameter

* Cleanup, minor issues

* Cuda compilation fixed and some minor fixes
2020-04-23 08:36:49 +10:00
raver119 2c80b18f1d disable mmap test for cuda
Signed-off-by: raver119 <raver119@gmail.com>
2020-04-22 12:57:26 +03:00
raver119 78260efe54 fix overallocation for memory-mapped workspaces
Signed-off-by: raver119 <raver119@gmail.com>
2020-04-22 12:38:22 +03:00
raver119 a10fd4524a
Fix for certain non-ews cases (#402)
* BtS/StB/StD/DtS dup for views

Signed-off-by: raver119 <raver119@gmail.com>

* batchnorm_bp dup for views

Signed-off-by: raver119 <raver119@gmail.com>

* two java tests for bad strides

Signed-off-by: raver119 <raver119@gmail.com>
2020-04-21 12:41:30 +03:00
raver119 5ee37a22eb
Workspace ID fix (#400)
Signed-off-by: raver119 <raver119@gmail.com>
2020-04-21 07:31:57 +03:00
Alex Black 76aab75174
Fix uberjar dependencies (#401)
Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-21 10:51:26 +10:00
Alex Black fe516ae6cf
nd4j-jackson dependency fix (#398)
* Remove old nd4j-jackson dependencies

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix use of old/deprecated JSON serializer

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix deserialization

Signed-off-by: Alex Black <blacka101@gmail.com>

* Delete test using deleted ser/de classes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Delete another copy of old test

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-20 22:33:11 +10:00
Alex Black 191bda3228
Base namespace (#287)
* wip

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* up to assign operation.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* fix Imax, IMin.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* concat.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* dynamicPartition

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* new ops up to gte.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* updated review items.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* up to matchCondition.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* up to OneHot.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip. up to permute.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip. up to rank.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip. up to scatterMul.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* resolving code review issues.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip. inclides UnsortedSegment ops.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip. up to stridedSlice.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* fix stridedSlice.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* first pass of SDBaseops.kt complete.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* fix review items.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* put branch in compilable state.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* add NDBaseTest. fix dynamicPartition signature. failed fix of assign.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* make tests public.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* adds tests up to invertedPermutation.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* fix ScalarEquals, Assign.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* wip

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* updates NDBaseTest.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* updates 'check' comments based on test pass/fail.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* fix scalar ops. Update tests,

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* dev-tools review items. wip.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* dev-tools code review items.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* Test fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* complete review items.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* Comment for logged issue; fix test case

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* More fixes

* wip

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* undo changes to Nd4jCpu.java

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* update tests.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* Fixes and regenerate

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Small test fixes

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* small fixes to tests.

Signed-off-by: Robert Altena <Rob@Ra-ai.com>

* Cleanup

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Small CUDAExecutioner fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Small CudaExecutioner fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* Another small CudaExecutioner fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* Another small CudaExecutioner fix

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Robert Altena <Rob@Ra-ai.com>
2020-04-20 16:57:00 +10:00
Alexander Stoyakin 455a5d112d
Fixes for codegen generated classes and build improvements (#367)
* Input format extended

* Deleted redundant code

* Added weights format to conv2d config

* Refactoring

* dl4j base test functionality

* Different tests base class per module

* Check base class for dl4j-graph subproject tests

* Check if test classes extend BaseDL4JTest

* Use nd4j-common-tests as transient dependency

* Enums and tests added

* Added codegenerated methods

* Use namespace methods

* Replace DifferentialFunctionFactory  with codegenerated classes

* Fixed linspace

* Namespaces regenerated

* Namespaces used instead of factory

* Regenerated base classes

* Input format extended

* Added weights format to conv2d config

* Refactoring

* dl4j base test functionality

* Different tests base class per module

* Check base class for dl4j-graph subproject tests

* Check if test classes extend BaseDL4JTest

* Use nd4j-common-tests as transient dependency

* Enums and tests added

* Added codegenerated methods

* Use namespace methods

* Replace DifferentialFunctionFactory  with codegenerated classes

* Fixed linspace

* Namespaces regenerated

* Regenerated base classes

* Regenerated namespaces

* Generate nd4j namespaces

* INDArrays accepting constructors

* Generated some ops

* Some fixes

* SameDiff ops regenerated

* Regenerated nd4j ops

* externalErrors moved

* Compilation fixes

* SquaredDifference - strict number of args

* Deprecated code cleanup. Proper base class for tests.

* Extend test classes with BaseND4JTest

* Extend test classes with BaseDL4JTest

* Legacy code

* DL4J cleanup

* Exclude test utils from base class check

* Tests fixed

* Arbiter tests fix

* Test dependency scope fix + pom.xml formatting

Signed-off-by: Alex Black <blacka101@gmail.com>

* Significant number of fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Another round of fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Another round of fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Few additional fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* DataVec missing test scope dependencies

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-20 10:27:13 +10:00
Alex Black 18d4eaa68d
DL4J SameDiff loss function (#251)
* Copied and pasted RegressionTest100b4.java to RegressionTest100b6.java with renamed b4->b6

* SameDiffLoss draft

* very very draft

* Copied and pasted RegressionTest100b4.java to RegressionTest100b6.java with renamed b4->b6

* temporary commit for clarification

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* temporary commit for clarification v2

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* temporary commit for clarification v3

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* temporary commit for clarification v3

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* Copied and pasted RegressionTest100b4.java to RegressionTest100b6.java with renamed b4->b6

* very very draft

* temporary commit for clarification

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* temporary commit for clarification v2

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* temporary commit for clarification v3

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* temporary commit for clarification v3

Signed-off-by: atuzhykov <andrewtuzhukov@gmail.com>

* SDLoss after requested changes but with questions in comments

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* added requested changes

* small fixes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Javadoc

Signed-off-by: Alex Black <blacka101@gmail.com>

* Test fix

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Andrii Tuzhykov <andrew@unrealists.com>
Co-authored-by: atuzhykov <andrewtuzhukov@gmail.com>
Co-authored-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>
2020-04-17 19:47:57 +10:00
Andrii T 5fbb04531d
At cpp ops (#378)
* crelu op added

* crelu op added

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* minor fixes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* crelu(bp)+transformOpValidation op

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* added ClipByAvgNorm and DepthwiseConv2DBp

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* ClipByAvgNorm passes forward check

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* EmbeddingLookup draft

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* DepthwiseConv2DB gradient check

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* EmbeddingLookup and DepthwiseConv2dBp finished + tests added

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* ImageResize draft

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* DepthwiseConv2DB gradient check

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* ImageResize passed tests except helper::resizeFunctor:Non implemented

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* replaced ImageResizeMethods enum by codegen

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* minor fixes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* polished checkpoint (OPValidationSuite passed and mvn install build succesfull after codegen)

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* manually merged LSTMLayerTestCases from master
Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* MaximumBp added and tested

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* MergeAddBp draft

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* MergeMaxBp and MergeAvgBP added and tests passed

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* minor fix

* draft LSTMLayerBp (big relative layer in gradient check)

* LSTMLayerBp check

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* LSTMLayerBp check v2

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* requested changes (test passes)

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* LSTMLayer testcases passed gradientcheck

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* small LSTMLayer testcase1 improvement (cLast, yLast)

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Warnings issue solved

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Fixes for MKLDNN LSTM layer helper

Signed-off-by: Alex Black <blacka101@gmail.com>

* stable version

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

Co-authored-by: raver119 <raver119@gmail.com>
Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-17 15:16:14 +10:00
Alex Black 3967e039a5
Switch Java-based updater implementations to C++ ops (#384)
Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-17 14:41:49 +10:00
Oleh 3d15706ffa
Lin_space operation improve (#373)
* libnd4j update linspace op

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j #8513 update lin_space op, tests added

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* - minor linspace tweaks (num_elements now iArg)
- java linspace updates
- couple of additional tests for linspace

Signed-off-by: raver119 <raver119@gmail.com>

* roll back timeout change

Signed-off-by: raver119 <raver119@gmail.com>

Co-authored-by: raver119 <raver119@gmail.com>
2020-04-16 14:53:56 +03:00
raver119 12ba1fa406
Few minor fixes (#381)
* - 1D indexing fix
- couple of new tests for 1D indexing

Signed-off-by: raver119 <raver119@gmail.com>

* percentile fix + test

Signed-off-by: raver119 <raver119@gmail.com>

* wrong signature used in test

Signed-off-by: raver119 <raver119@gmail.com>
2020-04-16 13:25:13 +03:00
raver119 75af392671
- memcpy fix + validation for CUDA: skip memcpu if length < 1 (#375)
- Reset cached context after device affinity change

Signed-off-by: raver119 <raver119@gmail.com>
2020-04-14 18:47:46 +03:00
Samuel Audet 6fcd078c5e
Update dependencies to just released JavaCPP and JavaCV 1.5.3 (#374)
Signed-off-by: Samuel Audet <samuel.audet@gmail.com>
2020-04-14 19:36:14 +10:00
raver119 3e2dbc65dd
MatMul for gemm/gemv calls (#365)
* libnd4j added optional alpha and beta support to matmul

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j typos fixes

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j add optional alpha and beta to matmul_bp

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j one more typo fix

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j added optional alpha and beta to mkl implementation

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* MatMul alpha/beta on java side

Signed-off-by: raver119 <raver119@gmail.com>

* alpha/beta fix in libnd4j

Signed-off-by: raver119 <raver119@gmail.com>

* alpha/beta fix in matmul_bp

Signed-off-by: raver119 <raver119@gmail.com>

* restored view validation

Signed-off-by: raver119 <raver119@gmail.com>

* gemv/gemm now use MatMul op

Signed-off-by: raver119 <raver119@gmail.com>

* few tests fixed

Signed-off-by: raver119 <raver119@gmail.com>

* additional INDArray.mmul signature

Signed-off-by: raver119 <raver119@gmail.com>

* make C order default for INDArray.mmul, unless both A/B have F order

Signed-off-by: raver119 <raver119@gmail.com>

* Nd4j.gemm validation fix

Signed-off-by: raver119 <raver119@gmail.com>

* disable mkldnn matmul for xxf with beta != 0 case

Signed-off-by: raver119 <raver119@gmail.com>

* SimpleRnn workspace fix + timeouts

Signed-off-by: Alex Black <blacka101@gmail.com>

* two more tests + minor fix in matmul platform check

Signed-off-by: raver119 <raver119@gmail.com>

* Flaky test fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* propagate testresources profile

Signed-off-by: raver119 <raver119@gmail.com>

* Resources fix + flaky test fix

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Oleg <oleg.semeniv@gmail.com>
Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-10 17:57:02 +03:00
Alex Black 99c727f15b
Add javacpp classifier dependency to nd4j-native and nd4j-cuda (#366)
Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-09 10:00:27 +10:00
Andrii T d86dd5b131
DL4J and SameDiff integration tests + LSTMLayer java op class (#353)
* init in this branch

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Lenetet Mnist workflow

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* small fix for calculations

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* for Alex to check placeholder null pointer issue

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* CNN3D workflow

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* state for launching on dxg to regenterate dl4j examples

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* SD RNN test case workflow

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* small fixes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* checkpoint at lstmBlock: Input array 1 (x) rank must be got input with rank 2 issue

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Fix LSTMLayer inputs order

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* lstm mismatch with c++ op issue

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* LSTMLayer config draft

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* LSTMLayer config draft v2

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* have doubt I had to do this

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* NDRNN generated by codegen

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* LSTMLayerTestCases draft

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* minor fixes again

* added LSTMLayer testcases to nd4j-tests + setted Preconditions in LSTMLayer constructors

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* added lost SDCNNtestcases

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* overrided getNumOutputs from DynamicCustomOp in LSTMLayer and reorganized LSTMLayerOutputs according to cpp op

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* finished with LSTMLayerOutputs

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Fix MKLDNN platform checks (i.e., when MKLDNN can be used vs. not)

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix LSTMLayerWeights input order

Signed-off-by: Alex Black <blacka101@gmail.com>

* More fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* minor fixes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* fixed LSTMLayer testcases

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* finished SameDiffRNNTestCase

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* finished all testcases + minor fixes

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Multiple generation-related fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix multiple issues

Signed-off-by: Alex Black <blacka101@gmail.com>

* More fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* LSTM fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Regenerate ND4J namespaces and fix multiple issues

Signed-off-by: Alex Black <blacka101@gmail.com>

* changed SameDiffRNNTestCase

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* Small fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* added  Nd4j.getRandom().setSeed(12345) where needed

Signed-off-by: Andrii Tuzhykov <andrewtuzhykov@gmail.com>

* #8828 Fix ND4J profiler NaN/Inf checks when using OpContext

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8828 Fix ND4J profiler NaN/Inf checks when using OpContext

Signed-off-by: Alex Black <blacka101@gmail.com>

* Tweak to weight init for SameDiff CNN test case

Signed-off-by: Alex Black <blacka101@gmail.com>

* Tweaks for test cases

Signed-off-by: Alex Black <blacka101@gmail.com>

* Ignore failing tests until fixed

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-09 00:20:48 +10:00
raver119 04b2b4f9b6
Few fixes (#361)
* INDArray.close() fix for CPU

Signed-off-by: raver119 <raver119@gmail.com>

* - BroadcastableBoolOp introduced
- ConfusionMatrix now supports explicit DataType argument

Signed-off-by: raver119 <raver119@gmail.com>

* confusion_matrix: dtype is still optional

Signed-off-by: raver119 <raver119@gmail.com>

* disable bert tests in debug builds

Signed-off-by: raver119 <raver119@gmail.com>

* Affinity fix

Signed-off-by: raver119 <raver119@gmail.com>

* minor workspace tweak to allow close() on scoped out borrowed workspace

Signed-off-by: raver119 <raver119@gmail.com>
2020-04-06 21:01:59 +03:00
Alex Black 986ec4b51a
Add test from reported issue (confirmed fixed) (#359)
Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-06 15:02:09 +10:00
Alexander Stoyakin fb1c41c512
Build fix (#357) 2020-04-01 19:09:48 +11:00
Yurii Shyrma 48102c61d0
- correct reshape op for empty shapes (#354)
* - correct reshape op for empty shape in case of -1 at the end

Signed-off-by: Yurii <iuriish@yahoo.com>

* Fix test + new reshape op constructor

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-01 15:13:34 +11:00
Alex Black 81ebfeead1
Small fixes (#355)
* #8787 DataVec test fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* New nd4j test + fix bad datavec test

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8745 Fix flaky arbiter test

Signed-off-by: Alex Black <blacka101@gmail.com>

* One more test

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-04-01 15:11:39 +11:00
Alexander Stoyakin 0a27e9f41d
Fix incompatibilities with generated code (#303)
* Cholesky fixed

* Constructors added

* MatMul wrapper

* Constructor added

* Missing wrappers added

* Generate Linalg namespace added

* Output data types

* Unit tests

* Added mmul

* Code generation

* Code generated

* Build fixed

* Fixing signatures

* Tests fixed

* Tests fixed

* Added enum

* Fix tests

* Some fixes

* Eye test fixed

* SameDiff: small fix for renameVariable - also replace variable name in lossVariable list if necessary

Signed-off-by: Alex Black <blacka101@gmail.com>

* Some fixes

* Tests fixed

* Revert wrong fix

* Some fixes

* Some fixes

* Extending base test class

* Added pad

* Fixed for generated signatures

* Fixes due to nd4j codegen

* Backwards compatibility fixes

* Fixed errors in tests, reverted wrong changes

* Test fixed

* Added missing operations used for nd4s operators

* Compilation fixed

* Added meshgrid

* Fixed constructors

* fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fix bad commit (incorrectly reverted change from master)

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fixed test

Co-authored-by: Alex Black <blacka101@gmail.com>
2020-04-01 12:00:38 +11:00
Alex Black 9b3576bc00 Merge remote-tracking branch 'eclipse/master' 2020-03-30 22:18:25 +11:00
Alex Black 63c9223bc2
Assorted fixes (#318)
* #8777 MultiLayerNetwork.evaluate(MultiDataSetIterator) overload

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8768 SameDiff.equals

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8750 shade freemarker library and switch to it in DL4J UI

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8704 DL4J UI redirect

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8776 RecordReaderDataSetIterator builder collectMetaData fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8718 Fix DL4J doEvaluation metadata

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8715 ArchiveUtils - Add option to not log every extracted file

Signed-off-by: Alex Black <blacka101@gmail.com>

* No exception for evaluations that don't support metadata

Signed-off-by: Alex Black <blacka101@gmail.com>

* Fixes

Signed-off-by: Alex Black <blacka101@gmail.com>

* #8765 CompGraph+MDS fix for SharedTrainingMaster

Signed-off-by: Alex Black <blacka101@gmail.com>

* small fix

Signed-off-by: Alex Black <blacka101@gmail.com>

* Timeout

Signed-off-by: Alex Black <blacka101@gmail.com>

* Ignore

Signed-off-by: Alex Black <blacka101@gmail.com>

* Revert freemarker shading

Signed-off-by: Alex Black <blacka101@gmail.com>

* Ignore

Signed-off-by: Alex Black <blacka101@gmail.com>
2020-03-27 00:33:13 +11:00
mheck136 364f9a660c
Set source and target version of nd4j-native to java 7 (#8808)
Signed-off-by: Martin Heck <mheck136@gmail.com>
2020-03-26 11:33:56 +11:00
Fariz Rahman b1bc7df160
tf.keras model import (#258)
* tf op initial

* ..

* protobuf parsing working

* model build working

* test passing

* headers

* conffix

* service loader + tests

* revert cuda version

* msg

* override

* refacc

* pom

* rem bad import

* dtype fix + const cast caaching

* rem unnecessary fields

* rem println

* rem dep

* refacc

* rem redundant arg

* Ignore TFOpLayer in DTypeTests

Signed-off-by: Alex Black <blacka101@gmail.com>

Co-authored-by: Alex Black <blacka101@gmail.com>
2020-03-24 20:37:27 +11:00