2404be5fe0
* libnd4j: Multinomial op #8570 first raw step of multinomial random data generator implementation Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op #8570 next step of multinomial random categories generator implementation on both cpu and cuda, need corrections and code clean up before review and testing * libnd4j: Multinomial op #8570 code clean up and fixed issues data selecting, moved from coords to tads * libnd4j: Multinomial op #8570 fixed cuda build add reference for math materials that was used for implementation * libnd4j: Multinomial op #8570 fixed several bugs, added several tests and improved cuda version. current implementation works, need testing of reproduction with the same seed * libnd4j: Multinomial op #8570 fixes and optimization after discussion in both cuda and cpu * libnd4j: Multinomial op #8570 add corrections after review, removed tads, replace 2D parallel loop by 3D Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op fixed declaration and add tests need discussion * libnd4j: Multinomial op fix in test * libnd4j: Multinomial op corrected behavior to get reproducible results, fixed issue in uniform value getting, tests added, need cuda review and cuda testing Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op fixed indexing on uniform calculation Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op some corrections in max min declaration Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op fixed index calculation, added rewind, corrected input declaration, added stats tests, both cuda and cpu. cuda need testing * libnd4j: Multinomial op fixed bugs on cuda nad cpu. need review Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op corrected tests to handle different orders Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op some improvements after code review Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op more corrections after review Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op fixed seed usage, update tests, fixed cuda based on comments, fixed bug of rewind, removed one behavior, minor corrections. Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op minor corrections Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op rise the bound of fluctuation for random cases Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j: Multinomial op modified operation inputs and update implementation and tests on both cpu and cuda * libnd4j: Multinomial op corrected data types according ops.proto Co-authored-by: raver119 <raver119@gmail.com>
Monorepo of Deeplearning4j
Welcome to the new monorepo of Deeplearning4j that contains the source code for all the following projects, in addition to the original repository of Deeplearning4j moved to deeplearning4j:
- https://github.com/eclipse/deeplearning4j/tree/master/libnd4j
- https://github.com/eclipse/deeplearning4j/tree/master/nd4j
- https://github.com/eclipse/deeplearning4j/tree/master/datavec
- https://github.com/eclipse/deeplearning4j/tree/master/arbiter
- https://github.com/eclipse/deeplearning4j/tree/master/nd4s
- https://github.com/eclipse/deeplearning4j/tree/master/gym-java-client
- https://github.com/eclipse/deeplearning4j/tree/master/rl4j
- https://github.com/eclipse/deeplearning4j/tree/master/scalnet
- https://github.com/eclipse/deeplearning4j/tree/master/pydl4j
- https://github.com/eclipse/deeplearning4j/tree/master/jumpy
- https://github.com/eclipse/deeplearning4j/tree/master/pydatavec
To build everything, we can use commands like
./change-cuda-versions.sh x.x
./change-scala-versions.sh 2.xx
./change-spark-versions.sh x
mvn clean install -Dmaven.test.skip -Dlibnd4j.cuda=x.x -Dlibnd4j.compute=xx
or
mvn -B -V -U clean install -pl '!jumpy,!pydatavec,!pydl4j' -Dlibnd4j.platform=linux-x86_64 -Dlibnd4j.chip=cuda -Dlibnd4j.cuda=9.2 -Dlibnd4j.compute=<your GPU CC> -Djavacpp.platform=linux-x86_64 -Dmaven.test.skip=true
An example of GPU "CC" or compute capability is 61 for Titan X Pascal.
Want some examples?
We have separate repository with various examples available: https://github.com/eclipse/deeplearning4j-examples
In the examples repo, you'll also find a tutorial series in Zeppelin: https://github.com/eclipse/deeplearning4j-examples/tree/master/tutorials