* error code check in CudaMemoryManager
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
* clear
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
* clear model before exiting
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
* MultiLayerNetwork/ComputationGraph.close() [WIP] (#460)
* MultiLayerNetwork/ComputationGraph.close()
Signed-off-by: Alex Black <blacka101@gmail.com>
* Copyright header
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix
Signed-off-by: Alex Black <blacka101@gmail.com>
* - fix for handling release of nested DataBuffers
- couple of additional tests for released DataBuffers
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
* PW test: increase number of epochs slightly
Signed-off-by: raver119@gmail.com <raver119@gmail.com>
Co-authored-by: Alex Black <blacka101@gmail.com>
* 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>
* merge conf
* merge conf
* tfkeras tests
* parameterized tests
* rename
* cuda versions
* jccp versions
* 'updates'
* updates
* rnn+mlp passing
* repeat
* updates
* tests
* Update pom.xml
* Update pom.xml
* rem print
* cnn1d model conversion fixed
* cnn1d activate fixed
* cnn1d outptut shape fix
* cnn1d bprop fix
* cnn1d stack fix
* KerasModelEndToEndTest - Remove permutes for NWC and NHWC format tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fixes and update test - input shapes (NCHW -> NHWC input)
Signed-off-by: Alex Black <blacka101@gmail.com>
* Ignore for known bad tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Multiple fixes - MergeVertex, CNN1D layers, etc
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix issue with RNN/FF preprocessors, time distributed etc with NWC format
Signed-off-by: Alex Black <blacka101@gmail.com>
* LSTM NWC dropout fix
Signed-off-by: Alex Black <blacka101@gmail.com>
* Add sequence embedding layer NWC support (configurable output format)
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix expected shape in a couple of tests - NWC expected
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix EmbeddingSequenceLayer backprop for NWC output case + add gradient checks
Signed-off-by: Alex Black <blacka101@gmail.com>
* CnnToFeedForwardPreprocessor: align with Keras/TF; fix Keras reshape/flatten
Signed-off-by: Alex Black <blacka101@gmail.com>
* Update ConvDataFormatTests to match new reshape behaviour
Signed-off-by: Alex Black <blacka101@gmail.com>
* Switch hard-coded path to ResourceUtils.listClassPathfiles for TestTFKerasModelImport
Signed-off-by: Alex Black <blacka101@gmail.com>
* TestUtils fix
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fixes
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix JSON serde issue with data formats
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix for input dtype inference; fix 2 tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Test fixes
Signed-off-by: Alex Black <blacka101@gmail.com>
* #8891 Ignore for TestVertxUIMultiSession until fixed
Signed-off-by: Alex Black <blacka101@gmail.com>
* Restore but deprecate TensorFlowCnnToFeedForwardPreProcessor for older zoo models
Signed-off-by: Alex Black <blacka101@gmail.com>
* Ignore for deprecated preprocessor in DTypeTests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Remove debug printlns
Signed-off-by: Alex Black <blacka101@gmail.com>
Co-authored-by: Alex Black <blacka101@gmail.com>
* 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
* First steps for DL4J NHWC support
Signed-off-by: Alex Black <blacka101@gmail.com>
* Conv2d NHWC forward pass works
Signed-off-by: Alex Black <blacka101@gmail.com>
* Conv2d NHWC backprop
Signed-off-by: Alex Black <blacka101@gmail.com>
* Conv2d backprop + fixes; subsampling fwd/bwd; improve tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Zero padding layer NHWC support
Signed-off-by: Alex Black <blacka101@gmail.com>
* Cropping2D NHWC support
Signed-off-by: Alex Black <blacka101@gmail.com>
* Deconv2d NHWC + clean up NHWC test framework code duplication
Signed-off-by: Alex Black <blacka101@gmail.com>
* CnnLossLayer NHWC support
Signed-off-by: Alex Black <blacka101@gmail.com>
* Upsampling and batchnorm NHWC support
Signed-off-by: Alex Black <blacka101@gmail.com>
* Space to depth
Signed-off-by: Alex Black <blacka101@gmail.com>
* Depthwise pt1
Signed-off-by: Alex Black <blacka101@gmail.com>
* Depthwise pt2 and LRN
Signed-off-by: Alex Black <blacka101@gmail.com>
* SpaceToBatch
Signed-off-by: Alex Black <blacka101@gmail.com>
* LocallyConnected2D
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix depthwise nhwc support
Signed-off-by: Alex Black <blacka101@gmail.com>
* Upsampling NHWC - workaround for #8857
Signed-off-by: Alex Black <blacka101@gmail.com>
* Workaround for #8859 - SpaceToDepth
Signed-off-by: Alex Black <blacka101@gmail.com>
* Batch normalization workaround - #8860
Signed-off-by: Alex Black <blacka101@gmail.com>
* cuDNN fixes
Signed-off-by: Alex Black <blacka101@gmail.com>
* Switch cudnn conv2d to permute based impl due to 'true' NHWC not working
Signed-off-by: Alex Black <blacka101@gmail.com>
* cuDNN subsampling helper NHWC fix
Signed-off-by: Alex Black <blacka101@gmail.com>
* Upsampling/batchnorm fixes
Signed-off-by: Alex Black <blacka101@gmail.com>
* Small fixes
Signed-off-by: Alex Black <blacka101@gmail.com>
* CNN2D NHWC gradient checks (make CNNGradientCheckTest parameterized)
Signed-off-by: Alex Black <blacka101@gmail.com>
* Gradient checks, SConv2d, bunch of fixes
Signed-off-by: Alex Black <blacka101@gmail.com>
* Small fixes
Signed-off-by: Alex Black <blacka101@gmail.com>
* Global pooling NHWC support
Signed-off-by: Alex Black <blacka101@gmail.com>
* Also test both float and double for cuDNN NHWC tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Javadoc
Signed-off-by: Alex Black <blacka101@gmail.com>
* Ignore failing keras import test until next PR
Signed-off-by: Alex Black <blacka101@gmail.com>
* Increase default timeout on Spark tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* #8840 disable deeplearning4j-nlp-korean module for scala 2.12
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix for change-scala-versions.sh
Signed-off-by: Alex Black <blacka101@gmail.com>
* CUDA test fixes + more timeout issues
Signed-off-by: Alex Black <blacka101@gmail.com>
* More CUDA
Signed-off-by: Alex Black <blacka101@gmail.com>
* Small fix for cuDNN subsampling + same mode
Signed-off-by: Alex Black <blacka101@gmail.com>
* Flaky test fix
Signed-off-by: Alex Black <blacka101@gmail.com>
* Reduce memory requirements for ValidateCuDNN BN test
Signed-off-by: Alex Black <blacka101@gmail.com>
* Fix slow/ineffirient scalnet tests
Signed-off-by: Alex Black <blacka101@gmail.com>
* Increase timeouts to avoid failures if CI machines are slower than expected
Signed-off-by: Alex Black <blacka101@gmail.com>
* Ignore flaky test (issue #8849) and increase timeout for slow CI downloads
Signed-off-by: Alex Black <blacka101@gmail.com>
* 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>
* 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>
* Allow scalar op result array auto allocation
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Don't swallow underlying exception for calculateOutputShape execution failures
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignore for known keras failure
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Timeouts added
* Added some ops
* Ops added
* Fixed tests
* Minor fix
* Some fixes
* Digamma added
* Small fixes
* Timeouts added
* Added some ops
* Ops added
* Fixed tests
* Minor fix
* Some fixes
* Digamma added
* Small fixes
* Fused batch norm fixes-
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tests switched off.
* Added test for resize_bicubic.
* Eliminated wasted in test of bicubic resize.
* Switched off multithreading explicit.
* HsvToRgb and RgbToHsv added
* Eliminated waste comments and conform proper float constants.
Signed-off-by: shugeo <sgazeos@gmail.com>
* Fixed multithreading with resize_bicubic helper for cpu platform.
Signed-off-by: shugeo <sgazeos@gmail.com>
* ResizeBicubic was fixed.
* Some fixes
* Fix op name
* Validation fixed.
* Clarifications for tests
* Wrappers and small fixes for new ops.
* Keras causal conv1d support first steps
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Add tests
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Causal conv mode
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Gradient check and fixes for causal conv1d
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix Conv1D import and testing
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Cleanup
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small keras test fix
Signed-off-by: Alex Black <blacka101@gmail.com>
* Don't allow setting causal convolution mode to conv2d/3d layers
Signed-off-by: Alex Black <blacka101@gmail.com>
* More robustly infer nIn for recurrent layers for ambiguous NCW and NWC cases
Signed-off-by: Alex Black <blacka101@gmail.com>
* Polish and cleanup
Signed-off-by: Alex Black <blacka101@gmail.com>
* #6377 Keras sparse cross entropy loss import support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix small bug in reshape preprocessor
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Capsnet test runtime improvements
* Slow test speedups
* Next round of test speed improvements
* More test improvements
* Improve test speed
* Next round of test speedups
* Another round
* More test speedups
* Another round
* Another round of test speedups
* Another round of speedups...
* CuDNN test speedups + more tests extending BaseDL4JTest
* Minor fix + more BaseDL4JTest use in other modules
