[GitHub] leezu commented on issue #10768: Use numpy in RandomSampler

leezu commented on issue #10768: Use numpy in RandomSampler URL: https://github.com/apache/incubator-mxnet/pull/10768#issuecomment-386511294 @asitstands above timings where taken with an array size of 12525568. I have tried again with size 4 and get the following: ``` In [3]:

[GitHub] szha commented on issue #10804: Use depthwise convolution(group convolution) by cuDNNv7 if available

szha commented on issue #10804: Use depthwise convolution(group convolution) by cuDNNv7 if available URL: https://github.com/apache/incubator-mxnet/pull/10804#issuecomment-386508424 @kice would you list some comparison on the speed and memory usage? also, does cudnn api have any

[GitHub] lionel92 opened a new issue #10807: Asnumpy() error with gluon dense under both GPU/CPU/MKLDNN environment

lionel92 opened a new issue #10807: Asnumpy() error with gluon dense under both GPU/CPU/MKLDNN environment URL: https://github.com/apache/incubator-mxnet/issues/10807 ## Description I try to use gluon API to test mkldnn while an error occurs when do asnumpy() operation after the

[GitHub] diyang commented on issue #10805: SKIP RNN is incorrect in LSTnet

diyang commented on issue #10805: SKIP RNN is incorrect in LSTnet URL: https://github.com/apache/incubator-mxnet/issues/10805#issuecomment-386503905 `stacked_rnn_cells = mx.rnn.SequentialRNNCell() for i, recurrent_cell in enumerate(skipcells): stacked_rnn_cells.add(recurrent_cell)

[GitHub] diyang commented on issue #10805: SKIP RNN is incorrect in LSTnet

diyang commented on issue #10805: SKIP RNN is incorrect in LSTnet URL: https://github.com/apache/incubator-mxnet/issues/10805#issuecomment-386503905 `stacked_rnn_cells = mx.rnn.SequentialRNNCell() for i, recurrent_cell in enumerate(skipcells): stacked_rnn_cells.add(recurrent_cell)

[GitHub] eric-haibin-lin opened a new pull request #10806: hide kvstore api from api index

eric-haibin-lin opened a new pull request #10806: hide kvstore api from api index URL: https://github.com/apache/incubator-mxnet/pull/10806 ## Description ## The kvstore in MXNet is implemented with lots of assumption and is dangerous to expose the API to users. We should consider

[GitHub] sl1pkn07 commented on issue #10558: NNVM build failed in the newst mxnet version

sl1pkn07 commented on issue #10558: NNVM build failed in the newst mxnet version URL: https://github.com/apache/incubator-mxnet/issues/10558#issuecomment-386503287 I can try build another gcc version. But need time to prepare the environment

[GitHub] lightingghost commented on issue #10220: Check failed: !ndinputs.back()->is_none()

lightingghost commented on issue #10220: Check failed: !ndinputs.back()->is_none() URL: https://github.com/apache/incubator-mxnet/issues/10220#issuecomment-375840105 Here is a minimum sample to reproduce this error ```python import mxnet as nd from mxnet import nd, sym,

[GitHub] altosaar commented on issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize?

altosaar commented on issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize? URL: https://github.com/apache/incubator-mxnet/issues/10781#issuecomment-386501819 Sweet, thanks! This is an

[GitHub] altosaar closed issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize?

altosaar closed issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize? URL: https://github.com/apache/incubator-mxnet/issues/10781 This is an automated message from the Apache Git

[GitHub] diyang opened a new issue #10805: SKIP RNN is incorrect in LSTnet

diyang opened a new issue #10805: SKIP RNN is incorrect in LSTnet URL: https://github.com/apache/incubator-mxnet/issues/10805 Thanks for your example and source code, it helps me a lot to develop my own LSTnet. However, I have noticed that there are some flaws in the implementation of

[GitHub] nihui commented on issue #10804: Use depthwise convolution(group convolution) by cuDNNv7 if available

nihui commented on issue #10804: Use depthwise convolution(group convolution) by cuDNNv7 if available URL: https://github.com/apache/incubator-mxnet/pull/10804#issuecomment-386499524 how about the speed improvment over mxnet native implementation ?

[GitHub] kice opened a new pull request #10804: Use depthwise convolution(group convolution) by cuDNNv7 if available

kice opened a new pull request #10804: Use depthwise convolution(group convolution) by cuDNNv7 if available URL: https://github.com/apache/incubator-mxnet/pull/10804 ## Description ## Use group convolution by cuDNNv7 to improve GPU memory usage. This commit is base on

[GitHub] threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386497664 @rahul003 For mpich, if you directly install ubuntu package of mpich, it's header file and lib file is

[incubator-mxnet] branch master updated: [MXNET-367] update mkldnn to v0.14 and disable building test examples (#10736)

This is an automated email from the ASF dual-hosted git repository. marcoabreu pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git The following commit(s) were added to refs/heads/master by this push: new 3c7afcc [MXNET-367] update mkldnn

[GitHub] marcoabreu closed pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples

marcoabreu closed pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples URL: https://github.com/apache/incubator-mxnet/pull/10736 This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the

[GitHub] nihui commented on issue #10726: Fix for cpp examples in mxnet/cpp-package.

nihui commented on issue #10726: Fix for cpp examples in mxnet/cpp-package. URL: https://github.com/apache/incubator-mxnet/pull/10726#issuecomment-386497173 hi I wonder why the change apply MNISTIter for alexnet googlenet inception_bn resnet, which should use ImageRecordIter anyway.

[incubator-mxnet] branch master updated: Fix row_sparse_pull with single gpu (#10772)

This is an automated email from the ASF dual-hosted git repository. haibin pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git The following commit(s) were added to refs/heads/master by this push: new 7395be8 Fix row_sparse_pull with

[GitHub] eric-haibin-lin closed pull request #10772: Fix row_sparse_pull with single gpu

eric-haibin-lin closed pull request #10772: Fix row_sparse_pull with single gpu URL: https://github.com/apache/incubator-mxnet/pull/10772 This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As this is

[GitHub] rahul003 commented on issue #10558: NNVM build failed in the newst mxnet version

rahul003 commented on issue #10558: NNVM build failed in the newst mxnet version URL: https://github.com/apache/incubator-mxnet/issues/10558#issuecomment-386495940 Hi @sl1pkn07, I realized this could have nothing to do with USE_F16C. The same failure exists on code from Nov 2017 with

[GitHub] rahul003 commented on issue #10558: NNVM build failed in the newst mxnet version

rahul003 commented on issue #10558: NNVM build failed in the newst mxnet version URL: https://github.com/apache/incubator-mxnet/issues/10558#issuecomment-386495940 Hi I realized this has nothing to do with USE_F16C. The same failure exists on code from Nov 2017 with gcc5.5. Similar

[GitHub] nihui opened a new pull request #10803: remove unused rotateM_

nihui opened a new pull request #10803: remove unused rotateM_ URL: https://github.com/apache/incubator-mxnet/pull/10803 ## Description ## the actual rotate param is allocated on demand, the rotateM_ member is useless remove it ## Checklist ## ### Essentials ### - [ ]

[GitHub] mangos47 commented on issue #10791: Unable to install mxnet in R 3.5.0

mangos47 commented on issue #10791: Unable to install mxnet in R 3.5.0 URL: https://github.com/apache/incubator-mxnet/issues/10791#issuecomment-386492201 I too am having difficulty installing mxnet r package after updating to R 3.5.0. The error is that it cannot download the package

[GitHub] kice commented on issue #7393: add depthwise convolution's gpu version optimization

kice commented on issue #7393: add depthwise convolution's gpu version optimization URL: https://github.com/apache/incubator-mxnet/pull/7393#issuecomment-386489332 Did someone do some tests the depthwise conv of cudnn v7 on Pascal GPU? I think we can get some performance improvement on

[GitHub] wkcn opened a new pull request #10802: fix the formula for LRN operator

wkcn opened a new pull request #10802: fix the formula for LRN operator URL: https://github.com/apache/incubator-mxnet/pull/10802 ## Description ## Fix the formula for LRN operator ## Testing Code ```python import numpy as np import mxnet as mx N, C, H, W =

[incubator-mxnet-site] branch asf-site updated: Bump the publish timestamp.

This is an automated email from the ASF dual-hosted git repository. zhasheng pushed a commit to branch asf-site in repository https://gitbox.apache.org/repos/asf/incubator-mxnet-site.git The following commit(s) were added to refs/heads/asf-site by this push: new 498ee5a Bump the publish

[GitHub] threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386484809 @rahul003 The build instruction is as follows: USE_DIST_KVSTORE = 1 USE_MPI_DIST_KVSTORE = 1

[GitHub] threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386487375 @rahul003 Local Batch Size: 64 means every node's batch size is 64 so global batch size is 64 * 8 = 512.

[GitHub] threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386484809 @rahul003 The build instruction is in the design doc. USE_DIST_KVSTORE = 1 USE_MPI_DIST_KVSTORE

[GitHub] threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386484809 @rahul003 The build instruction is in the design doc. USE_DIST_KVSTORE = 1 USE_MPI_DIST_KVSTORE

[GitHub] threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

threeleafzerg commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386484809 @rahul003 The build instruction is in the design doc. USE_DIST_KVSTORE = 1 USE_MPI_DIST_KVSTORE

[GitHub] TaoLv commented on issue #10773: specify common arch for mkldnn build, so it can be reused on all arch

TaoLv commented on issue #10773: specify common arch for mkldnn build, so it can be reused on all arch URL: https://github.com/apache/incubator-mxnet/pull/10773#issuecomment-386484645 @szha Just to add, I greped in mxnet project and found there is a flag `USE_SSE`. Not sure about the

[GitHub] roywei commented on issue #10788: Start a process for training. The training get stuck

roywei commented on issue #10788: Start a process for training. The training get stuck URL: https://github.com/apache/incubator-mxnet/issues/10788#issuecomment-386478639 @huyangc Using the mnist example in a process is working fine, could you provide more detailed information? Like

[GitHub] ashokei commented on issue #10591: [MXNET-365] handle inplace in mkldnn FallBackCompute

ashokei commented on issue #10591: [MXNET-365] handle inplace in mkldnn FallBackCompute URL: https://github.com/apache/incubator-mxnet/pull/10591#issuecomment-386476616 @piiswrong ping... This is an automated message from

[GitHub] ashokei commented on a change in pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples

ashokei commented on a change in pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples URL: https://github.com/apache/incubator-mxnet/pull/10736#discussion_r185970854 ## File path: ci/docker/install/ubuntu_mklml.sh ## @@ -21,5 +21,5 @@

[GitHub] xu2011 commented on issue #10793: dataloader load custom dataset error

xu2011 commented on issue #10793: dataloader load custom dataset error URL: https://github.com/apache/incubator-mxnet/issues/10793#issuecomment-386476409 problem resolved, thank you This is an automated message from the

[GitHub] chinakook commented on issue #10799: Feature Request for SoftmaxCrossEntropyLoss with Ignore labels

chinakook commented on issue #10799: Feature Request for SoftmaxCrossEntropyLoss with Ignore labels URL: https://github.com/apache/incubator-mxnet/issues/10799#issuecomment-386476504 F.SoftmaxOutput is a solution but without weighting

[GitHub] xu2011 closed issue #10793: dataloader load custom dataset error

xu2011 closed issue #10793: dataloader load custom dataset error URL: https://github.com/apache/incubator-mxnet/issues/10793 This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] roywei commented on issue #10776: make clean USE_MKLDNN=1 triggers MKLDNN build

roywei commented on issue #10776: make clean USE_MKLDNN=1 triggers MKLDNN build URL: https://github.com/apache/incubator-mxnet/issues/10776#issuecomment-386475800 @sandeep-krishnamurthy could you help to add label Build? Thanks

[GitHub] roywei commented on issue #10784: Flaky memory error

roywei commented on issue #10784: Flaky memory error URL: https://github.com/apache/incubator-mxnet/issues/10784#issuecomment-386475600 @reminisce could you help to add label Build? Thanks This is an automated message from

[GitHub] roywei commented on issue #10778: Make android error

roywei commented on issue #10778: Make android error URL: https://github.com/apache/incubator-mxnet/issues/10778#issuecomment-386475700 @sandeep-krishnamurthy could you help to add label installation/build? Thanks! This

[GitHub] roywei commented on issue #10782: Multiple calls to mx.sym.Variable with same name: Dangerous / unexpected behavior?

roywei commented on issue #10782: Multiple calls to mx.sym.Variable with same name: Dangerous / unexpected behavior? URL: https://github.com/apache/incubator-mxnet/issues/10782#issuecomment-386475435 @julian90 using the same name is not recommended, please refer to #9890 and #2036.

[GitHub] roywei commented on issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize?

roywei commented on issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize? URL: https://github.com/apache/incubator-mxnet/issues/10781#issuecomment-386474928 @reminisce could you help to add label Gluon? Thanks

[GitHub] roywei commented on issue #10786: Feature request: square op for row_sparse and sum op with keepdims

roywei commented on issue #10786: Feature request: square op for row_sparse and sum op with keepdims URL: https://github.com/apache/incubator-mxnet/issues/10786#issuecomment-386474759 @eric-haibin-lin could you help to add label feature request and sparse? Thanks!

[GitHub] roywei commented on issue #10789: Reshape of input array when the shape is available only at runtime is not possible

roywei commented on issue #10789: Reshape of input array when the shape is available only at runtime is not possible URL: https://github.com/apache/incubator-mxnet/issues/10789#issuecomment-386473739 Can we make this a feature request and add the label? Thanks!

[GitHub] roywei commented on issue #10791: Unable to install mxnet in R 3.5.0

roywei commented on issue #10791: Unable to install mxnet in R 3.5.0 URL: https://github.com/apache/incubator-mxnet/issues/10791#issuecomment-386473578 @nswamy Could you help to add label R and installation? Thanks! This is

[GitHub] roywei commented on issue #10793: dataloader load custom dataset error

roywei commented on issue #10793: dataloader load custom dataset error URL: https://github.com/apache/incubator-mxnet/issues/10793#issuecomment-386473397 @xu2011 Please refer to [default batchify

[GitHub] roywei commented on issue #10801: CMake ignores USE_MKLDNN flag for 1.2.0.RC[0-2] releases

roywei commented on issue #10801: CMake ignores USE_MKLDNN flag for 1.2.0.RC[0-2] releases URL: https://github.com/apache/incubator-mxnet/issues/10801#issuecomment-386472316 @anirudh2290 could you add relevant labels (installation/build/MKL) to keep track? Thanks

[GitHub] roywei commented on issue #10799: Feature Request for SoftmaxCrossEntropyLoss with Ignore labels

roywei commented on issue #10799: Feature Request for SoftmaxCrossEntropyLoss with Ignore labels URL: https://github.com/apache/incubator-mxnet/issues/10799#issuecomment-386472798 @nswamy could you help to add label feature request, performance? Thanks

[GitHub] roywei commented on issue #10801: CMake ignores USE_MKLDNN flag for 1.2.0.RC[0-2] releases

roywei commented on issue #10801: CMake ignores USE_MKLDNN flag for 1.2.0.RC[0-2] releases URL: https://github.com/apache/incubator-mxnet/issues/10801#issuecomment-386472316 @anirudh2290 could you add relevant labels (build/MKL) to keep track? Thanks

[GitHub] ShownX commented on issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize?

ShownX commented on issue #10781: Gluon HybridBlock: how to use functions outside of class and still hybridize? URL: https://github.com/apache/incubator-mxnet/issues/10781#issuecomment-386458890 Define another class inherit the ```hybridizeBlock``` and put the function in the

[GitHub] anirudh2290 opened a new issue #10801: CMake ignores USE_MKLDNN flag for 1.2.0.RC[0-2] releases

anirudh2290 opened a new issue #10801: CMake ignores USE_MKLDNN flag for 1.2.0.RC[0-2] releases URL: https://github.com/apache/incubator-mxnet/issues/10801 CMake ignores the `USE_MKLDNN` flag for 1.2.RC2 release. This has been fixed in the master as part of #10731. To workaround the issue

[GitHub] eric-haibin-lin commented on issue #9686: APIs that might be a good idea to break in 2.0

eric-haibin-lin commented on issue #9686: APIs that might be a good idea to break in 2.0 URL: https://github.com/apache/incubator-mxnet/issues/9686#issuecomment-386451698 kvstore should not be public API This is an

[GitHub] zhreshold commented on issue #10794: fix topk nms in multibox_detection operator

zhreshold commented on issue #10794: fix topk nms in multibox_detection operator URL: https://github.com/apache/incubator-mxnet/pull/10794#issuecomment-386451296 The CI failed with unrelated error. Can you rebase against master and push again? @arcadiaphy

[GitHub] piiswrong opened a new pull request #10800: Update index.md

piiswrong opened a new pull request #10800: Update index.md URL: https://github.com/apache/incubator-mxnet/pull/10800 ## Description ## (Brief description on what this PR is about) ## Checklist ## ### Essentials ### Please feel free to remove inapplicable items for your PR.

[incubator-mxnet] 01/01: Update index.md

This is an automated email from the ASF dual-hosted git repository. jxie pushed a commit to branch piiswrong-patch-2 in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git commit 0d1927cd915eb91d99c56cf67915d22a2343a62b Author: Eric Junyuan Xie

[incubator-mxnet] branch piiswrong-patch-2 created (now 0d1927c)

This is an automated email from the ASF dual-hosted git repository. jxie pushed a change to branch piiswrong-patch-2 in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git. at 0d1927c Update index.md This branch includes the following new commits: new 0d1927c

[GitHub] piiswrong commented on issue #10793: dataloader load custom dataset error

piiswrong commented on issue #10793: dataloader load custom dataset error URL: https://github.com/apache/incubator-mxnet/issues/10793#issuecomment-386448613 DataLoader doesn't know how to convert raw bytes to batches. you need to provide a custom batchify_fn.

[GitHub] rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-38644 I installed MPI with `sudo apt-get install mpich` on ubuntu and gave MPIROOT as /usr/local/bin/mpi . Build

[GitHub] szha closed pull request #10622: [MXNET-341] Added General Info to API Docs for Python and Gluon

szha closed pull request #10622: [MXNET-341] Added General Info to API Docs for Python and Gluon URL: https://github.com/apache/incubator-mxnet/pull/10622 This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of

[incubator-mxnet] branch master updated: Added more information to API Docs for Python and Gluon. (#10622)

This is an automated email from the ASF dual-hosted git repository. zhasheng pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git The following commit(s) were added to refs/heads/master by this push: new 4e68b3b Added more information to

[GitHub] aaronmarkham commented on issue #10622: [MXNET-341] Added General Info to API Docs for Python and Gluon

aaronmarkham commented on issue #10622: [MXNET-341] Added General Info to API Docs for Python and Gluon URL: https://github.com/apache/incubator-mxnet/pull/10622#issuecomment-386410687 I can't... maybe @szha or @eric-haibin-lin can.

[GitHub] rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386407788 @threeleafzerg Could you share instructions for building this, and add this as a step to the CI to verify the

[GitHub] zhanghang1989 opened a new issue #10799: Feature Request for SoftmaxCrossEntropyLoss with Ignore labels

zhanghang1989 opened a new issue #10799: Feature Request for SoftmaxCrossEntropyLoss with Ignore labels URL: https://github.com/apache/incubator-mxnet/issues/10799 Although we can implement this using existing operators, but current implementation is not efficient and very memory

[GitHub] rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386408856 About the numbers above 'Local Batch Size: 64' refers to 64 across many GPUs? Can you run a benchmark with

[GitHub] rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386408856 About the numbers above 'Local Batch Size: 64' refers to 64 across many GPUs? Can you run a benchmark with

[GitHub] rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

rahul003 commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386407788 @threeleafzerg Could you share instructions for building this, and add this as a step to the CI to verify the

[GitHub] marcoabreu commented on a change in pull request #10797: Better cleaning of git repo, signal handlers

marcoabreu commented on a change in pull request #10797: Better cleaning of git repo, signal handlers URL: https://github.com/apache/incubator-mxnet/pull/10797#discussion_r185907848 ## File path: ci/docker/runtime_functions.sh ## @@ -353,7 +369,18 @@ sanity_check() { }

[GitHub] marcoabreu commented on a change in pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples

marcoabreu commented on a change in pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples URL: https://github.com/apache/incubator-mxnet/pull/10736#discussion_r185906646 ## File path: ci/docker/install/ubuntu_mklml.sh ## @@ -21,5 +21,5

[GitHub] marcoabreu commented on a change in pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples

marcoabreu commented on a change in pull request #10736: [MXNET-367] update mkldnn to v0.14 and disable building test examples URL: https://github.com/apache/incubator-mxnet/pull/10736#discussion_r185906485 ## File path: ci/docker/install/ubuntu_mklml.sh ## @@ -21,5 +21,5

[GitHub] sandeep-krishnamurthy closed issue #10187: OpenCV 3.3.1 undefined reference to compiler CXX_3.4.21

sandeep-krishnamurthy closed issue #10187: OpenCV 3.3.1 undefined reference to compiler CXX_3.4.21 URL: https://github.com/apache/incubator-mxnet/issues/10187 This is an automated message from the Apache Git Service. To

[GitHub] lanking520 commented on a change in pull request #10660: [MXNET-357] New Scala API Design (Symbol)

lanking520 commented on a change in pull request #10660: [MXNET-357] New Scala API Design (Symbol) URL: https://github.com/apache/incubator-mxnet/pull/10660#discussion_r185900243 ## File path: scala-package/macros/src/main/scala/org/apache/mxnet/SymbolMacro.scala ## @@

[GitHub] marcoabreu closed pull request #10798: Revert "update the performance page of MXNet."

marcoabreu closed pull request #10798: Revert "update the performance page of MXNet." URL: https://github.com/apache/incubator-mxnet/pull/10798 This is an automated message from the Apache Git Service. To respond to the

[GitHub] marcoabreu commented on issue #10798: Revert "update the performance page of MXNet."

marcoabreu commented on issue #10798: Revert "update the performance page of MXNet." URL: https://github.com/apache/incubator-mxnet/pull/10798#issuecomment-386390109 I spoke to Steffen and we'll update this after 1.2 has been released

[GitHub] marcoabreu opened a new pull request #10798: Revert "update the performance page of MXNet."

marcoabreu opened a new pull request #10798: Revert "update the performance page of MXNet." URL: https://github.com/apache/incubator-mxnet/pull/10798 Reverts apache/incubator-mxnet#10761 This is an automated message from the

[GitHub] piiswrong commented on issue #10731: Fix a bug in getting MKLDNN memory

piiswrong commented on issue #10731: Fix a bug in getting MKLDNN memory URL: https://github.com/apache/incubator-mxnet/pull/10731#issuecomment-386373182 intel people saids generic is ok. I'm going to assume they know what they are talking about

[GitHub] piiswrong closed pull request #10731: Fix a bug in getting MKLDNN memory

piiswrong closed pull request #10731: Fix a bug in getting MKLDNN memory URL: https://github.com/apache/incubator-mxnet/pull/10731 This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As this is a

[GitHub] haojin2 commented on a change in pull request #10533: [MXNET-314] Support Integer Type parsing in CSVIter

haojin2 commented on a change in pull request #10533: [MXNET-314] Support Integer Type parsing in CSVIter URL: https://github.com/apache/incubator-mxnet/pull/10533#discussion_r185878246 ## File path: src/io/iter_csv.cc ## @@ -54,27 +57,90 @@ struct CSVIterParam : public

[GitHub] piiswrong closed pull request #10767: add reverse option to ndarray inplace reshape

piiswrong closed pull request #10767: add reverse option to ndarray inplace reshape URL: https://github.com/apache/incubator-mxnet/pull/10767 This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As

[incubator-mxnet] branch master updated: add reverse option to ndarray inplace reshape (#10767)

This is an automated email from the ASF dual-hosted git repository. jxie pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git The following commit(s) were added to refs/heads/master by this push: new 66b2944 add reverse option to ndarray

[GitHub] piiswrong commented on issue #10795: Op for scaled attention

piiswrong commented on issue #10795: Op for scaled attention URL: https://github.com/apache/incubator-mxnet/pull/10795#issuecomment-386361516 I think it's better to have an op like get_shape and do x = x/mx.sym.get_shape(x)[-1]

[GitHub] thomelane commented on issue #10622: [MXNET-341] Added General Info to API Docs for Python and Gluon

thomelane commented on issue #10622: [MXNET-341] Added General Info to API Docs for Python and Gluon URL: https://github.com/apache/incubator-mxnet/pull/10622#issuecomment-386352736 @aaronmarkham @indhub can either of you merge this pr?

[GitHub] WellyZhang commented on issue #3432: OSError: /usr/lib/libgdal.so.1: undefined symbol: sqlite3_column_table_name

WellyZhang commented on issue #3432: OSError: /usr/lib/libgdal.so.1: undefined symbol: sqlite3_column_table_name URL: https://github.com/apache/incubator-mxnet/issues/3432#issuecomment-386348874 @cipri-tom Generally, most Anaconda libs should work (some are actually just links to sys

[GitHub] luoyetx commented on issue #10544: name_scope/prefix doesn't work

luoyetx commented on issue #10544: name_scope/prefix doesn't work URL: https://github.com/apache/incubator-mxnet/issues/10544#issuecomment-386329043 @Ghostish #10695 This is an automated message from the Apache Git Service.

[GitHub] Ghostish commented on issue #10544: name_scope/prefix doesn't work

Ghostish commented on issue #10544: name_scope/prefix doesn't work URL: https://github.com/apache/incubator-mxnet/issues/10544#issuecomment-386298387 I am facing the same problem. Could you please tell me how to solve it ?

[GitHub] larroy commented on issue #10797: Better cleaning of git repo

larroy commented on issue #10797: Better cleaning of git repo URL: https://github.com/apache/incubator-mxnet/pull/10797#issuecomment-386289719 @marcoabreu This is an automated message from the Apache Git Service. To respond

[GitHub] marcoabreu commented on a change in pull request #10731: Fix a bug in getting MKLDNN memory

marcoabreu commented on a change in pull request #10731: Fix a bug in getting MKLDNN memory URL: https://github.com/apache/incubator-mxnet/pull/10731#discussion_r185789666 ## File path: ci/docker/runtime_functions.sh ## @@ -313,16 +313,22 @@

[GitHub] pengzhao-intel commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce

pengzhao-intel commented on issue #10696: [MXNET-366]Extend MXNet Distributed Training by MPI AllReduce URL: https://github.com/apache/incubator-mxnet/pull/10696#issuecomment-386281938 @mli @rahul003 Could you help take the review for this PR?

[GitHub] larroy opened a new pull request #10797: Better cleaning of git repo

larroy opened a new pull request #10797: Better cleaning of git repo URL: https://github.com/apache/incubator-mxnet/pull/10797 ## Description ## (Brief description on what this PR is about) ## Checklist ## ### Essentials ### Please feel free to remove inapplicable items for

[GitHub] lx75249 commented on issue #6313: cpp-package: Cannot open include file: 'mxnet-cpp/op.h'

lx75249 commented on issue #6313: cpp-package: Cannot open include file: 'mxnet-cpp/op.h' URL: https://github.com/apache/incubator-mxnet/issues/6313#issuecomment-386258172 @Rangocold Do you have openblas dll registered?

[GitHub] juliusshufan commented on issue #10765: Gluon-based image-classification failed to run with dummy data on CPU machine when set as "symbolic" mode

juliusshufan commented on issue #10765: Gluon-based image-classification failed to run with dummy data on CPU machine when set as "symbolic" mode URL: https://github.com/apache/incubator-mxnet/issues/10765#issuecomment-38625 @roywei I tried the PR from @zheng-da

[GitHub] juliusshufan opened a new pull request #10796: Test case improvement for MKLDNN on Gluon

juliusshufan opened a new pull request #10796: Test case improvement for MKLDNN on Gluon URL: https://github.com/apache/incubator-mxnet/pull/10796 ## Description ## This PR is a "follow-up" of previously merged https://github.com/apache/incubator-mxnet/pull/10764 In this PR, we are

[GitHub] Rangocold commented on issue #6313: cpp-package: Cannot open include file: 'mxnet-cpp/op.h'

Rangocold commented on issue #6313: cpp-package: Cannot open include file: 'mxnet-cpp/op.h' URL: https://github.com/apache/incubator-mxnet/issues/6313#issuecomment-386248197 i meet the same problem but my error tip is 7>"Running: OpWrapperGenerator.py

[GitHub] paoloviviani commented on issue #8126: Not able to train a neural network [XOR added]

paoloviviani commented on issue #8126: Not able to train a neural network [XOR added] URL: https://github.com/apache/incubator-mxnet/issues/8126#issuecomment-386244730 I'm also experiencing the same problem here, but with LinearRegressionOutput (even with a single neuron and no

[GitHub] TaoLv commented on issue #10104: [WIP][MXNET-107] Fused RNN implementation for CPU

TaoLv commented on issue #10104: [WIP][MXNET-107] Fused RNN implementation for CPU URL: https://github.com/apache/incubator-mxnet/pull/10104#issuecomment-386243514 LSTM functionality is done. Reviewers are asking for dropout support for multi-layer RNN. Will work on that.

[GitHub] wangshuailong commented on issue #7070: AttributeError: 'module' object has no attribute 'CaffeOp'

wangshuailong commented on issue #7070: AttributeError: 'module' object has no attribute 'CaffeOp' URL: https://github.com/apache/incubator-mxnet/issues/7070#issuecomment-386225588 I had the same problem minutes ago, it turned out that I set the wrong environment path which was still the

[GitHub] wangshuailong commented on issue #7070: AttributeError: 'module' object has no attribute 'CaffeOp'

wangshuailong commented on issue #7070: AttributeError: 'module' object has no attribute 'CaffeOp' URL: https://github.com/apache/incubator-mxnet/issues/7070#issuecomment-386225588 I had the same problem minutes ago, it turned out that I set the wrong environment path which was still the

[GitHub] sxjscience opened a new pull request #10795: Op for scaled attention

sxjscience opened a new pull request #10795: Op for scaled attention URL: https://github.com/apache/incubator-mxnet/pull/10795 ## Description ## Operator for scaled attention ## Checklist ## ### Essentials ### Please feel free to remove inapplicable items for your PR.

[GitHub] asitstands commented on issue #10768: Use numpy in RandomSampler

asitstands commented on issue #10768: Use numpy in RandomSampler URL: https://github.com/apache/incubator-mxnet/pull/10768#issuecomment-386209676 @leezu If possible, could I ask one more test? In my experiments, mxnet's shuffle outperforms numpy's when array size is large. Would you please

[GitHub] arcadiaphy opened a new pull request #10794: fix topk nms in multibox_detection operator

arcadiaphy opened a new pull request #10794: fix topk nms in multibox_detection operator URL: https://github.com/apache/incubator-mxnet/pull/10794 ## Description ## This PR fixes a bug in multibox_detection operator. According to operator documentation, only topk detections are kept

  1   2   >