zheshipinyinMc commented on issue #15207: Mack-RCNN C++ Deployment Not Working
in GPU Mode And CPU Mode
URL:
https://github.com/apache/incubator-mxnet/issues/15207#issuecomment-501131699
@zhreshold I just make may incubator-mxnet again with command 'make -j
$(nproc) USE_OPENCV=1
Zha0q1 commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292755064
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
szha commented on a change in pull request #15171: Upgrade archive utility and
add back FC improvement
URL: https://github.com/apache/incubator-mxnet/pull/15171#discussion_r292752614
##
File path: docs/install/build_from_source.md
##
@@ -180,6 +180,8 @@ More information
xinyu-intel commented on issue #11756: [MXNET-677] int8 quantization does not
work on toy mnist dataset
URL:
https://github.com/apache/incubator-mxnet/issues/11756#issuecomment-501127017
@ThomasDelteil add this line `sym =
sym.get_backend_symbol('MKLDNN_QUANTIZE')` to enable subgraph
This is an automated email from the ASF dual-hosted git repository.
lanking pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git.
from d32a3da [MKLDNN] Fix quantized act and concat (#15209)
add 29fea48 Readd Java HelloWorld example
lanking520 merged pull request #15217: Readd Java HelloWorld example for
intellij tutorial
URL: https://github.com/apache/incubator-mxnet/pull/15217
This is an automated message from the Apache Git Service.
To respond to
lanking520 closed issue #15204: java hello world demo is missing
URL: https://github.com/apache/incubator-mxnet/issues/15204
This is an automated message from the Apache Git Service.
To respond to the message, please log on
sandeep-krishnamurthy commented on a change in pull request #15171: Upgrade
archive utility and add back FC improvement
URL: https://github.com/apache/incubator-mxnet/pull/15171#discussion_r292743917
##
File path: docs/install/build_from_source.md
##
@@ -180,6 +180,8 @@
roywei commented on issue #15213: Fix horovod build failure when mxnet is built
from source
URL: https://github.com/apache/incubator-mxnet/pull/15213#issuecomment-501114092
I don't think re-trigger CI is going to pass, is there any way to fix CMake
errors in CI?
mouryarishik commented on issue #15193: How to calculate gradients for the
intermediate outputs using symbol?
URL:
https://github.com/apache/incubator-mxnet/issues/15193#issuecomment-501110582
I’ve seen this issue but can’t figure out what do I need to do. It confuses
me further because
nicklhy opened a new issue #15218: memory leak of ImageRecordIter ?
URL: https://github.com/apache/incubator-mxnet/issues/15218
Hi, all
I have a very big dataset (over 20 million pics) which has been split and
transformed into multiple recordio files. Thus, I wrote a custom data_iter
mxnet-label-bot commented on issue #15218: memory leak of ImageRecordIter ?
URL:
https://github.com/apache/incubator-mxnet/issues/15218#issuecomment-501105654
Hey, this is the MXNet Label Bot.
Thank you for submitting the issue! I will try and suggest some labels so
that the
pengzhao-intel commented on issue #11756: [MXNET-677] int8 quantization does
not work on toy mnist dataset
URL:
https://github.com/apache/incubator-mxnet/issues/11756#issuecomment-501100092
@ThomasDelteil the fused version of convolution can work with INT8 [in
TaoLv commented on a change in pull request #15213: Fix horovod build failure
when mxnet is built from source
URL: https://github.com/apache/incubator-mxnet/pull/15213#discussion_r292723098
##
File path: include/mkldnn/mkldnn.h
##
@@ -0,0 +1 @@
zheshipinyinMc commented on issue #15207: Mack-RCNN C++ Deployment Not Working
in GPU Mode And CPU Mode
URL:
https://github.com/apache/incubator-mxnet/issues/15207#issuecomment-501090919
@zhreshold test on server with GPU, the image(1000w*591h) needs about 10G
memory,the image(500w*295h)
zachgk opened a new pull request #15217: Readd Java HelloWorld example for
intellij tutorial
URL: https://github.com/apache/incubator-mxnet/pull/15217
## Description ##
This PR adds back the java HelloWorld demo that was removed as part of
#14213 to fix the intellij on java tutorial.
This is an automated email from the ASF dual-hosted git repository.
patriczhao 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 d32a3da [MKLDNN] Fix quantized
pengzhao-intel merged pull request #15209: [MKLDNN] Fix quantized act and concat
URL: https://github.com/apache/incubator-mxnet/pull/15209
This is an automated message from the Apache Git Service.
To respond to the message,
pengzhao-intel commented on issue #15209: [MKLDNN] Fix quantized act and concat
URL: https://github.com/apache/incubator-mxnet/pull/15209#issuecomment-501085167
Thanks, merging now.
This is an automated message from the
anirudh2290 commented on issue #10988: Flaky test:
test_operator_gpu.test_countsketch
URL:
https://github.com/apache/incubator-mxnet/issues/10988#issuecomment-501083385
Reopening since this again failed here :
This is an automated email from the ASF dual-hosted git repository.
marcoabreu 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 5e114d6 Bump the publish
eric-haibin-lin opened a new issue #10988: Flaky test:
test_operator_gpu.test_countsketch
URL: https://github.com/apache/incubator-mxnet/issues/10988
http://jenkins.mxnet-ci.amazon-ml.com/blue/organizations/jenkins/incubator-mxnet/detail/PR-10983/1/pipeline/
```
zhreshold commented on issue #15214: ImageRecordIter interpolation method
(inter_method) fails for NN (0)
URL:
https://github.com/apache/incubator-mxnet/issues/15214#issuecomment-501080332
Your point is right, would you like to submit a fix for it?
zachgk commented on issue #15193: How to calculate gradients for the
intermediate outputs using symbol?
URL:
https://github.com/apache/incubator-mxnet/issues/15193#issuecomment-501077581
Maybe try using BlockGrad like in
https://github.com/apache/incubator-mxnet/issues/1538?
zachgk commented on issue #15214: ImageRecordIter interpolation method
(inter_method) fails for NN (0)
URL:
https://github.com/apache/incubator-mxnet/issues/15214#issuecomment-501074995
@zhreshold Can you take a look?
This
chinakook commented on issue #13216: [Feature request]JPEG Orientation in
mxnet.image.imread
URL:
https://github.com/apache/incubator-mxnet/issues/13216#issuecomment-501073236
Yes, we can close it.
This is an automated
chinakook closed issue #13216: [Feature request]JPEG Orientation in
mxnet.image.imread
URL: https://github.com/apache/incubator-mxnet/issues/13216
This is an automated message from the Apache Git Service.
To respond to the
stu1130 commented on a change in pull request #15161: Numpy compatible max
URL: https://github.com/apache/incubator-mxnet/pull/15161#discussion_r292706948
##
File path: src/operator/mshadow_op.h
##
@@ -27,6 +27,7 @@
#define MXNET_OPERATOR_MSHADOW_OP_H_
#include
haojin2 commented on a change in pull request #15161: Numpy compatible max
URL: https://github.com/apache/incubator-mxnet/pull/15161#discussion_r292706143
##
File path: src/operator/mshadow_op.h
##
@@ -27,6 +27,7 @@
#define MXNET_OPERATOR_MSHADOW_OP_H_
#include
pengzhao-intel commented on issue #15118: Conversion from FP32 model to Mixed
Precision model
URL: https://github.com/apache/incubator-mxnet/pull/15118#issuecomment-501062972
@anirudh2290 thanks for great works and we are working on BF16 enabling in
local.
So I am asking @ZhennanQin
ZhennanQin commented on a change in pull request #15187: Improve static
cached_op optimization
URL: https://github.com/apache/incubator-mxnet/pull/15187#discussion_r292697012
##
File path: src/imperative/cached_op.cc
##
@@ -290,7 +290,7 @@ bool
This is an automated email from the ASF dual-hosted git repository.
zhasheng pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git.
from 1c3e964 fix the cmake cmd with wrong path (#15111)
add 62a85f3 Broken link fixes for the website
szha merged pull request #15205: Broken link fixes for the website
URL: https://github.com/apache/incubator-mxnet/pull/15205
This is an automated message from the Apache Git Service.
To respond to the message, please log on
pengzhao-intel commented on issue #15207: Mack-RCNN C++ Deployment Not Working
in GPU Mode And CPU Mode
URL:
https://github.com/apache/incubator-mxnet/issues/15207#issuecomment-501056909
@zheshipinyinMc this issue in MKLDNN backend should be fixed by
access2rohit commented on issue #15132: Profiler API Enhancements
URL: https://github.com/apache/incubator-mxnet/pull/15132#issuecomment-501053986
sure! Zhaoqi has fixed the failing tests now
This is an automated message
zachgk commented on issue #15192: Confusing Total params in
mxnet.visualization.print_summary
URL:
https://github.com/apache/incubator-mxnet/issues/15192#issuecomment-501053195
If you are looking for information about FullyConnected, you can check the
docs at
zachgk commented on issue #14732: cpp-package predict error at 'int best_idx =
predicted.At(0, 0)' whether the ndarray.hpp have a bug?
URL:
https://github.com/apache/incubator-mxnet/issues/14732#issuecomment-501044158
I am closing this issue as it should be resolved as part of #15179.
zachgk closed issue #14732: cpp-package predict error at 'int best_idx =
predicted.At(0, 0)' whether the ndarray.hpp have a bug?
URL: https://github.com/apache/incubator-mxnet/issues/14732
This is an automated message from
stu1130 commented on issue #15161: Numpy compatible max
URL: https://github.com/apache/incubator-mxnet/pull/15161#issuecomment-501043296
ping @haojin2 for 2nd review
This is an automated message from the Apache Git Service.
yuxihu commented on a change in pull request #15213: Fix horovod build failure
when mxnet is built from source
URL: https://github.com/apache/incubator-mxnet/pull/15213#discussion_r292679777
##
File path: include/mkldnn/mkldnn.h
##
@@ -0,0 +1 @@
zachgk opened a new pull request #15216: Add missing file to Maven clean
URL: https://github.com/apache/incubator-mxnet/pull/15216
## Description ##
Add missing generated file `SymbolBase.scala` to the list of files to be
deleted by maven clean.
@lanking520 @aaronmarkham
piyushghai commented on issue #15212: Confusing build from source instructions
URL:
https://github.com/apache/incubator-mxnet/issues/15212#issuecomment-501034872
@mxnet-label-bot Update[Doc, Unclear Error/Doc, Installation, Build]
piyushghai commented on issue #15212: Confusing build from source instructions
URL:
https://github.com/apache/incubator-mxnet/issues/15212#issuecomment-501034661
I don't think this is a Bug.
It's an issue with Installation instructions on the Website.
zachgk commented on issue #15191: How to load model parameters in jar packages
using java predictor
URL:
https://github.com/apache/incubator-mxnet/issues/15191#issuecomment-501032544
@rongruosong What you could do is copy all of the parameters from the jar to
a temporary directory. Then,
marcoabreu commented on a change in pull request #15187: Improve static
cached_op optimization
URL: https://github.com/apache/incubator-mxnet/pull/15187#discussion_r292668526
##
File path: src/imperative/cached_op.cc
##
@@ -290,7 +290,7 @@ bool
ThomasDelteil commented on issue #11756: [MXNET-677] int8 quantization does not
work on toy mnist dataset
URL:
https://github.com/apache/incubator-mxnet/issues/11756#issuecomment-501029690
@xinyu-intel @PatricZhao is there work to support `int8` type in MKLDNN ?
Currently it only
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292666198
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292665584
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
piyushghai edited a comment on issue #14228: Weird gluon hybridize bug
URL:
https://github.com/apache/incubator-mxnet/issues/14228#issuecomment-501027831
@yifeim There seems to be a workaround with wrapping inner network's y in
``` F.identity()``` .
Are you still facing the error ?
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292665176
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
piyushghai commented on issue #14228: Weird gluon hybridize bug
URL:
https://github.com/apache/incubator-mxnet/issues/14228#issuecomment-501027831
@yifeim There seems to be a workaround with wrapping inner network's y in
``` F.identity()``` .
Are you still facing the error ?
If
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292665238
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292665054
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292663306
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292663193
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
larroy commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292662487
##
File path: src/engine/threaded_engine.cc
##
@@ -333,9 +333,11 @@ void
Zha0q1 removed a comment on issue #15132: Profiler API Enhancements
URL: https://github.com/apache/incubator-mxnet/pull/15132#issuecomment-500248951
@marcoabreu Hi Marco, I have tried rebasing and some tests are still
failing. I think it is not related my changes. Could you help me take a
sandeep-krishnamurthy commented on issue #15132: Profiler API Enhancements
URL: https://github.com/apache/incubator-mxnet/pull/15132#issuecomment-501019471
@access2rohit - Can you please help review this PR?
This is an
larroy commented on issue #14940: Work on warnings
URL: https://github.com/apache/incubator-mxnet/pull/14940#issuecomment-501017864
@haojin2 can you please review again?
This is an automated message from the Apache Git
larroy commented on a change in pull request #15109: [DOC] refine autograd docs
URL: https://github.com/apache/incubator-mxnet/pull/15109#discussion_r292653783
##
File path: docs/api/python/autograd/autograd.md
##
@@ -76,7 +82,63 @@ Detailed tutorials are available in Part
Zha0q1 commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292653208
##
File path: src/operator/custom/custom-inl.h
##
@@ -76,7 +77,8 @@ class CustomOperator {
This is an automated email from the ASF dual-hosted git repository.
marcoabreu 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 03f659a Bump the publish
Zha0q1 commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292650120
##
File path: src/profiler/profiler.h
##
@@ -1149,8 +1158,20 @@ struct ProfileOperator : public
piyushghai commented on issue #12369: batchnorm from scratch with autograd
gives very different gradient from mx.nd.BatchNorm
URL:
https://github.com/apache/incubator-mxnet/issues/12369#issuecomment-501014298
I posted this question on the MXNet Discuss Forum as well to get a wider
ptrendx commented on issue #15198: Need a debugging utility to dump out
intermediate values of Tensor object
URL:
https://github.com/apache/incubator-mxnet/issues/15198#issuecomment-501012861
Monitor callback is good (although not really documented properly - I had to
look at the
access2rohit commented on issue #15210: [WIP] Custom Operator Profiling
Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#issuecomment-501012840
Even if the PR is WIP add the description and explain briefly what feature
are you adding to MXNet profiler and show how it
access2rohit commented on a change in pull request #15210: [WIP] Custom
Operator Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292643814
##
File path: src/operator/custom/custom-inl.h
##
@@ -76,7 +77,8 @@ class CustomOperator
access2rohit commented on a change in pull request #15210: [WIP] Custom
Operator Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292642862
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to
anirudh2290 commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292635460
##
File path: src/profiler/profiler.h
##
@@ -1225,6 +1250,10 @@ struct ProfileOperator :
anirudh2290 commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292634241
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to the
anirudh2290 commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292621044
##
File path: src/engine/threaded_engine.cc
##
@@ -333,9 +333,11 @@ void
anirudh2290 commented on a change in pull request #15210: [WIP] Custom Operator
Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292642328
##
File path: src/profiler/profiler.h
##
@@ -1149,8 +1158,20 @@ struct ProfileOperator :
access2rohit commented on a change in pull request #15210: [WIP] Custom
Operator Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#discussion_r292642085
##
File path: src/profiler/custom_op_profiler.h
##
@@ -0,0 +1,93 @@
+/*
+* Licensed to
access2rohit commented on issue #15210: [WIP] Custom Operator Profiling
Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#issuecomment-501002582
There are no test cases associated with this new feature introduction.
Please add test cases.
kohr-h commented on a change in pull request #13143: [MXNET-1206] Support
NDArray indexing with None and Ellipsis
URL: https://github.com/apache/incubator-mxnet/pull/13143#discussion_r292636720
##
File path: tests/python/unittest/test_ndarray.py
##
@@ -1292,7 +1358,9 @@
kohr-h commented on a change in pull request #13143: [MXNET-1206] Support
NDArray indexing with None and Ellipsis
URL: https://github.com/apache/incubator-mxnet/pull/13143#discussion_r292636254
##
File path: python/mxnet/ndarray/ndarray.py
##
@@ -387,19 +388,15 @@ def
piyushghai commented on issue #12369: batchnorm from scratch with autograd
gives very different gradient from mx.nd.BatchNorm
URL:
https://github.com/apache/incubator-mxnet/issues/12369#issuecomment-500997103
I don't reckon this is related to the tagged issue Anirudh.
In this case,
kohr-h commented on a change in pull request #13143: [MXNET-1206] Support
NDArray indexing with None and Ellipsis
URL: https://github.com/apache/incubator-mxnet/pull/13143#discussion_r292630634
##
File path: tests/python/unittest/test_operator.py
##
@@ -4388,13 +4388,14
kohr-h commented on a change in pull request #13143: [MXNET-1206] Support
NDArray indexing with None and Ellipsis
URL: https://github.com/apache/incubator-mxnet/pull/13143#discussion_r292627078
##
File path: tests/python/unittest/test_ndarray.py
##
@@ -1208,22 +1266,24 @@
kohr-h commented on a change in pull request #13143: [MXNET-1206] Support
NDArray indexing with None and Ellipsis
URL: https://github.com/apache/incubator-mxnet/pull/13143#discussion_r292627078
##
File path: tests/python/unittest/test_ndarray.py
##
@@ -1208,22 +1266,24 @@
kohr-h commented on a change in pull request #13143: [MXNET-1206] Support
NDArray indexing with None and Ellipsis
URL: https://github.com/apache/incubator-mxnet/pull/13143#discussion_r292626182
##
File path: tests/python/unittest/test_ndarray.py
##
@@ -1208,22 +1266,24 @@
chandana1332 commented on a change in pull request #15195: Fixed a bug in Gluon
DataLoader.
URL: https://github.com/apache/incubator-mxnet/pull/15195#discussion_r292622758
##
File path: python/mxnet/gluon/data/dataloader.py
##
@@ -409,7 +409,7 @@ def
This is an automated email from the ASF dual-hosted git repository.
marcoabreu 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 41fae9a Bump the publish
anirudhacharya commented on issue #13216: [Feature request]JPEG Orientation in
mxnet.image.imread
URL:
https://github.com/apache/incubator-mxnet/issues/13216#issuecomment-500982175
this issue is being tracked here -
https://github.com/apache/incubator-mxnet/issues/14956 Can we close this
anirudhacharya commented on issue #14956: mxnet.image.imread can not correctly
read jpg with orientation
URL:
https://github.com/apache/incubator-mxnet/issues/14956#issuecomment-500981903
@ksellesk this is the doc for opencv's imread -
satyakrishnagorti closed issue #14256: MXNet hangs when creating an NDArray on
a GPU Context in Scala
URL: https://github.com/apache/incubator-mxnet/issues/14256
This is an automated message from the Apache Git Service.
To
satyakrishnagorti commented on issue #14256: MXNet hangs when creating an
NDArray on a GPU Context in Scala
URL:
https://github.com/apache/incubator-mxnet/issues/14256#issuecomment-500976924
@andrewfayres I am unable to reproduce this in docker and don't have more
time to look into this
anirudh2290 commented on issue #15118: Conversion from FP32 model to Mixed
Precision model
URL: https://github.com/apache/incubator-mxnet/pull/15118#issuecomment-500975221
@Vikas89 @mseth10 @larroy @access2rohit @stu1130 @rondogency @Zha0q1
@samskalicky @apeforest @yuxihu
anirudh2290 commented on issue #15171: Upgrade archive utility and add back FC
improvement
URL: https://github.com/apache/incubator-mxnet/pull/15171#issuecomment-500972388
@larroy @samskalicky @sandeep-krishnamurthy @Chancebair please help review.
apeforest commented on a change in pull request #15213: Fix horovod build
failure when mxnet is built from source
URL: https://github.com/apache/incubator-mxnet/pull/15213#discussion_r292605592
##
File path: include/mkldnn/mkldnn.h
##
@@ -0,0 +1 @@
apeforest commented on a change in pull request #15213: Fix horovod build
failure when mxnet is built from source
URL: https://github.com/apache/incubator-mxnet/pull/15213#discussion_r292605592
##
File path: include/mkldnn/mkldnn.h
##
@@ -0,0 +1 @@
jschmitz28 commented on issue #15215: MXNet Row Sparse SGD Update fails when
Row Sparse weights are sparsely populated
URL:
https://github.com/apache/incubator-mxnet/issues/15215#issuecomment-500969382
Note that I think this might be related to
haojin2 opened a new issue #14978: Flaky Test:
test_tensorrt_lenet5.test_tensorrt_inference
URL: https://github.com/apache/incubator-mxnet/issues/14978
Happening for 2 independent PRs.
anirudh2290 commented on issue #14978: Flaky Test:
test_tensorrt_lenet5.test_tensorrt_inference
URL:
https://github.com/apache/incubator-mxnet/issues/14978#issuecomment-500966509
Reopening, still encountered this here:
mxnet-label-bot commented on issue #15215: MXNet Row Sparse SGD Update fails
when Row Sparse weights are sparsely populated
URL:
https://github.com/apache/incubator-mxnet/issues/15215#issuecomment-500966175
Hey, this is the MXNet Label Bot.
Thank you for submitting the issue! I will
zhreshold commented on a change in pull request #15195: Fixed a bug in Gluon
DataLoader.
URL: https://github.com/apache/incubator-mxnet/pull/15195#discussion_r292586944
##
File path: python/mxnet/gluon/data/dataloader.py
##
@@ -409,7 +409,7 @@ def
zhreshold commented on issue #15207: Mack-RCNN C++ Deployment Not Working in
GPU Mode And CPU Mode
URL:
https://github.com/apache/incubator-mxnet/issues/15207#issuecomment-500953751
@zheshipinyinMc For CPU you can try disable MKLDNN in your build see if it
works.
For GPU, it's
vandanavk commented on issue #15210: [WIP] Custom Operator Profiling Enhancement
URL: https://github.com/apache/incubator-mxnet/pull/15210#issuecomment-500950256
@mxnet-label-bot add [Operator, pr-work-in-progress]
This is an
yuxihu commented on a change in pull request #15213: Fix horovod build failure
when mxnet is built from source
URL: https://github.com/apache/incubator-mxnet/pull/15213#discussion_r292580691
##
File path: include/mkldnn/mkldnn.h
##
@@ -0,0 +1 @@
stu1130 commented on a change in pull request #15161: Numpy compatible max
URL: https://github.com/apache/incubator-mxnet/pull/15161#discussion_r292580063
##
File path: src/operator/numpy/np_broadcast_reduce_op.h
##
@@ -152,6 +170,38 @@ inline bool
1 - 100 of 154 matches
Mail list logo