kthr commented on issue #9794: MKL linker error on macOS 10.13 despite using
configuration without MKL
URL:
https://github.com/apache/incubator-mxnet/issues/9794#issuecomment-365854471
My issue is that tried to compile MXNet with the BLAS libraries shipped by
Apple using USE_BLAS=apple,
kthr commented on issue #9794: MKL linker error on macOS 10.13 despite using
configuration without MKL
URL:
https://github.com/apache/incubator-mxnet/issues/9794#issuecomment-365854471
My issue is that tried to compile MXNet with the BLAS libraries shipped by
Apple using USE_BLAS=apple,
kthr commented on issue #9794: MKL linker error on macOS 10.13 despite using
configuration without MKL
URL:
https://github.com/apache/incubator-mxnet/issues/9794#issuecomment-365854471
My issue is that tried to compile MXNet with the BLAS libraries shipped by
Apple using USE_BLAS=apple,
kthr commented on issue #9794: MKL linker error on macOS 10.13 despite using
configuration without MKL
URL:
https://github.com/apache/incubator-mxnet/issues/9794#issuecomment-365853404
@sandeep-krishnamurthy Thank you for the hint, but as I understand it, there
is no GPU enabled
samhodge commented on issue #8537: [Gluon] F.pad(...) doesn't accept symbol
input even in HybridBlock?
URL:
https://github.com/apache/incubator-mxnet/issues/8537#issuecomment-366127318
Thanks @masahi Did you find a style transfer that was fast that could take a
Symbol input?
jeremiedb opened a new pull request #9803: Metrics
URL: https://github.com/apache/incubator-mxnet/pull/9803
- Port metrics calculation to NDArrays and let the calculations on the
devices (rather than after copying on cpu). Performance is similar for general
cases, but significant for
dwSun commented on a change in pull request #9614: MobileNetV2
URL: https://github.com/apache/incubator-mxnet/pull/9614#discussion_r168662680
##
File path: python/mxnet/gluon/model_zoo/vision/mobilenet.py
##
@@ -74,13 +124,71 @@ def hybrid_forward(self, F, x):
x =
jeremiedb opened a new issue #9804: [R] mx.io.arrayiter shuffing is disabled
URL: https://github.com/apache/incubator-mxnet/issues/9804
`mx.io.arrayiter` shuffling option is no longer working, the option only
result in the first and last samples to be swapped. Likely appeared at the same
fhieber commented on issue #9686: APIs that might be a good idea to remove in
2.0
URL:
https://github.com/apache/incubator-mxnet/issues/9686#issuecomment-365913714
- consistent use of "axis"/"dim(s)" keyword arguments in all operators, for
example:
- swapaxes uses dim1, dim2
-
alues closed pull request #9796: Install Script Added
URL: https://github.com/apache/incubator-mxnet/pull/9796
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 foreign pull request
alues opened a new pull request #9797: Install Script Added
URL: https://github.com/apache/incubator-mxnet/pull/9797
EZ way to deploy mxnet Env
This is an automated message from the Apache Git Service.
To respond to the
m-ky commented on issue #8870: [clang][warning] fix warnings about braced
initializer (fixes warning in concurrenc?
URL: https://github.com/apache/incubator-mxnet/pull/8870#issuecomment-365911366
Commit: 343256f8f740998ef78eb49cacfb908dac0cf72d
larroy commented on issue #9686: APIs that might be a good idea to remove in 2.0
URL:
https://github.com/apache/incubator-mxnet/issues/9686#issuecomment-365912913
Refactors of the cpp-package and other C++ APIs. I would like that.
dwSun commented on issue #9614: MobileNetV2
URL: https://github.com/apache/incubator-mxnet/pull/9614#issuecomment-365869593
unittest finished.
This is an automated message from the Apache Git Service.
To respond to the
yajiedesign opened a new pull request #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798
## Description ##
fix cmake build error with vs
## Checklist ##
### Essentials ###
- [X] Passed code style checking (`make lint`)
- [X] Changes are complete
fhieber commented on issue #9686: APIs that might be a good idea to remove in
2.0
URL:
https://github.com/apache/incubator-mxnet/issues/9686#issuecomment-365913714
consistent use of "axis"/"dim(s)" keyword arguments in all operators, for
example:
- swapaxes uses dim1, dim2
-
alues opened a new pull request #9796: Install Script Added
URL: https://github.com/apache/incubator-mxnet/pull/9796
EZ way to have mxnet env
This is an automated message from the Apache Git Service.
To respond to the
arnaghizadeh commented on issue #9765: Installation with GPU on Fedora 27?
URL:
https://github.com/apache/incubator-mxnet/issues/9765#issuecomment-365953905
BTW here is the error with a clean install (e.g., without compiling the CPU
version first)
`git clone --recursive
cjolivier01 commented on a change in pull request #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#discussion_r168544696
##
File path: CMakeLists.txt
##
@@ -46,6 +46,11 @@ if(USE_CUDA AND NOT USE_OLDCMAKECUDA)
(${CMAKE_VERSION}
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168588353
##
File path: tests/cpp/operator/tune/operator_tune_test.cc
##
@@ -18,13 +18,14 @@
*/
#include
marcoabreu commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366053368
Where is it stated that operator tuning is not supported on Windows? Do
users get a proper error message? Also, I don't see why we should
marcoabreu commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366042988
To me, it really sounds like there are quite a decent number of known issues
but for whatever reason, there's a push to get this merged.
cjolivier01 commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366043180
" features being forgotten"? what features?
This is an automated message
cjolivier01 commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366043337
Operator Tuning was never supported on Windows and has nothing to do with
this PR.
lebeg opened a new pull request #9799: Cleaned up image classification cpp
example
URL: https://github.com/apache/incubator-mxnet/pull/9799
## Description ##
Cleaned up image classification cpp example.
## Checklist ##
### Essentials ###
- [x] Passed code style checking
piiswrong commented on issue #9797: Install Script Added
URL: https://github.com/apache/incubator-mxnet/pull/9797#issuecomment-366014732
We already have a set of install scripts. Please edit those instead of
adding a submodule
szha commented on issue #9672: CMake CUDA fixes + NCCL
URL: https://github.com/apache/incubator-mxnet/pull/9672#issuecomment-366014009
@cjolivier01 would you provide reasoning why conversation was locked?
According to the github's feature guideline, it's for defusing a heated
larroy commented on issue #9784: Fix for the case where there are no detections
URL: https://github.com/apache/incubator-mxnet/pull/9784#issuecomment-366014557
@cjolivier01 no, what's your point? its intention is semantic. instead of
just using a 0 index which is not clear what it
larroy commented on a change in pull request #9784: Fix for the case where
there are no detections
URL: https://github.com/apache/incubator-mxnet/pull/9784#discussion_r168562368
##
File path: example/ssd/detect/detector.py
##
@@ -136,31 +132,52 @@ class names
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366014736
Anyway, I think we should understand why this is problematic. It works on my
machine and in CI. It isn't ideal that version isn't auto-detected. When it
is set
piiswrong closed pull request #9797: Install Script Added
URL: https://github.com/apache/incubator-mxnet/pull/9797
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 foreign pull request
piiswrong commented on a change in pull request #9790: make array.reshape
compatible with numpy
URL: https://github.com/apache/incubator-mxnet/pull/9790#discussion_r168565856
##
File path: python/mxnet/ndarray/ndarray.py
##
@@ -968,6 +973,14 @@ def reshape(self, shape):
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168570700
##
File path: tests/cpp/include/test_core_op.h
##
@@ -311,68 +339,166 @@ class CoreOpExecutor : public
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168572280
##
File path: tests/cpp/operator/batchnorm_test.cc
##
@@ -1599,6 +1510,7 @@ TEST(BATCH_NORM,
sethah commented on issue #9777: [MX-9588] Add micro averaging strategy for F1
metric
URL: https://github.com/apache/incubator-mxnet/pull/9777#issuecomment-366027233
Thanks all for the review!
This is an automated message
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168576406
##
File path: tests/cpp/include/test_core_op.h
##
@@ -311,68 +339,166 @@ class CoreOpExecutor : public
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168576406
##
File path: tests/cpp/include/test_core_op.h
##
@@ -311,68 +339,166 @@ class CoreOpExecutor : public
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168579364
##
File path: tests/cpp/include/test_core_op.h
##
@@ -311,68 +339,166 @@ class CoreOpExecutor : public
larroy commented on a change in pull request #9677: Refactor operators and add
MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168579350
##
File path: CMakeLists.txt
##
@@ -610,7 +611,18 @@ endif()
if(USE_OPENCV)
add_executable(im2rec
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168579525
##
File path: tests/cpp/operator/batchnorm_test.cc
##
@@ -901,36 +1054,29 @@
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168579543
##
File path: tests/cpp/operator/batchnorm_test.cc
##
@@ -1599,6 +1510,7 @@ TEST(BATCH_NORM,
piiswrong commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366033743
Arguments for merging this PR despite the disabled cpp tests:
1. Python (and other language) tests passes. The frontend tests are the
marcoabreu commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366033667
I've talked offline to @piiswrong and he stated that the disabled tests are
covered by Python tests. I didn't verify that statement, but I
szha commented on issue #9672: CMake CUDA fixes + NCCL
URL: https://github.com/apache/incubator-mxnet/pull/9672#issuecomment-366014009
@cjolivier01 would you provide reasoning why conversation was locked?
According to the github's feature guideline, it's for defusing a heated
conversation
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366014067
Ok, I wasn't aware that it said that
This is an automated message from the Apache Git Service.
To
larroy commented on a change in pull request #9799: Cleaned up image
classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#discussion_r168561588
##
File path:
example/image-classification/predict-cpp/image-classification-predict.cc
##
@@
piiswrong commented on issue #9799: Cleaned up image classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#issuecomment-366013956
Those keys are release signing keys. If you are not going to drive a release
you don't need it
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366014736
Anyway, I think we should understand why this is problematic. It works on my
machine and in CI. It isn't ideal that version isn't auto-detected. When it
is set
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366014736
Anyway, I think we should understand why the current version is problematic.
It works on my machine and in CI. It isn't ideal that version isn't
auto-detected.
larroy commented on a change in pull request #9784: Fix for the case where
there are no detections
URL: https://github.com/apache/incubator-mxnet/pull/9784#discussion_r168562368
##
File path: example/ssd/detect/detector.py
##
@@ -136,31 +132,52 @@ class names
szha commented on a change in pull request #9790: make array.reshape compatible
with numpy
URL: https://github.com/apache/incubator-mxnet/pull/9790#discussion_r168566530
##
File path: python/mxnet/ndarray/ndarray.py
##
@@ -968,6 +973,14 @@ def reshape(self, shape):
marcoabreu commented on issue #9799: Cleaned up image classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#issuecomment-366020688
Could you please add on which platforms you have tested your modifications?
Since we're not testing examples on CI, we'll have to
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168573437
##
File path: tests/cpp/operator/tune/operator_tune_test.cc
##
@@ -18,13 +18,14 @@
*/
#include
piiswrong commented on a change in pull request #8972: Profiling enhancements,
python API, vtune and chrome tracing objects, etc.
URL: https://github.com/apache/incubator-mxnet/pull/8972#discussion_r168573339
##
File path: python/mxnet/profiler.py
##
@@ -52,7 +58,298 @@
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168573854
##
File path: tests/python/gpu/test_gluon_model_zoo_gpu.py
##
@@ -0,0 +1,171 @@
+# Licensed to the
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168573685
##
File path: tests/python/gpu/test_gluon_model_zoo_gpu.py
##
@@ -0,0 +1,171 @@
+# Licensed to the
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168575480
##
File path: tests/cpp/operator/tune/operator_tune_test.cc
##
@@ -18,13 +18,14 @@
*/
#include
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168575667
##
File path: tests/cpp/operator/batchnorm_test.cc
##
@@ -1599,6 +1510,7 @@ TEST(BATCH_NORM,
larroy commented on a change in pull request #9677: Refactor operators and add
MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168580648
##
File path: src/common/exec_utils.h
##
@@ -43,19 +43,61 @@ namespace common {
indices are not
marcoabreu commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366033667
I've talked offline to @piiswrong and he stated that the disabled tests are
covered by Python tests. I didn't verify that statement, but I
cjolivier01 commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366034644
There's only two out of 10-or-15-or-so tests that are disabled.
I am fine with the merge from the point of the cpp tests. Although
szha commented on issue #9672: CMake CUDA fixes + NCCL
URL: https://github.com/apache/incubator-mxnet/pull/9672#issuecomment-366011197
CMake cuda build was broken, reported by @yajiedesign. Fix is in #9798
This is an
zhreshold commented on a change in pull request #9614: MobileNetV2
URL: https://github.com/apache/incubator-mxnet/pull/9614#discussion_r168559118
##
File path: python/mxnet/gluon/model_zoo/vision/mobilenet.py
##
@@ -74,13 +124,71 @@ def hybrid_forward(self, F, x):
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366012745
It was reviewed. There is no rule that someone has to click "Approve". Where
does it say that? In fact, it was determined that it doesn't have to have that
szha commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366015154
Agreed. I can help create an issue to track this.
This is an automated message from the Apache Git
szha commented on issue #9672: CMake CUDA fixes + NCCL
URL: https://github.com/apache/incubator-mxnet/pull/9672#issuecomment-366014009
@cjolivier01 would you provide reasoning why conversation was locked?
According to the github's feature guideline, it's for defusing a heated
alues commented on issue #9797: Install Script Added
URL: https://github.com/apache/incubator-mxnet/pull/9797#issuecomment-366016473
script aim to build from source and deploy cuda & cudnn kit from none
This is an automated
marcoabreu commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366019016
I'd rather prefer to tell the user that the selected version is not present
and fail properly instead of automatically assuming a version. This could
otherwise
marcoabreu commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366019016
I'd rather prefer to tell the user that the selected version is not present
and fail gracefully instead of automatically assuming a version. This could
otherwise
szha commented on a change in pull request #9790: make array.reshape compatible
with numpy
URL: https://github.com/apache/incubator-mxnet/pull/9790#discussion_r168567197
##
File path: python/mxnet/ndarray/ndarray.py
##
@@ -968,6 +973,14 @@ def reshape(self, shape):
szha commented on a change in pull request #9790: make array.reshape compatible
with numpy
URL: https://github.com/apache/incubator-mxnet/pull/9790#discussion_r168567182
##
File path: python/mxnet/ndarray/ndarray.py
##
@@ -968,6 +973,14 @@ def reshape(self, shape):
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168572085
##
File path: tests/cpp/operator/batchnorm_test.cc
##
@@ -901,36 +1054,29 @@
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168572193
##
File path: tests/cpp/include/test_core_op.h
##
@@ -209,6 +209,13 @@ class CoreOpExecutor : public
piiswrong commented on a change in pull request #8972: Profiling enhancements,
python API, vtune and chrome tracing objects, etc.
URL: https://github.com/apache/incubator-mxnet/pull/8972#discussion_r168573339
##
File path: python/mxnet/profiler.py
##
@@ -52,7 +58,298 @@
cjolivier01 commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168575796
##
File path: tests/cpp/operator/batchnorm_test.cc
##
@@ -901,36 +1054,29 @@
marcoabreu commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366030149
But the user is selecting the version in config.mk, right? If that' the
case, then I'd say it's valid to tell the user that the selected version is not
present.
szha commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366011877
I think this constitutes a revert for the above referenced PR, which wasn't
approved and was self-merged (something we committers all agreed not to do).
I'd
szha commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366014314
No problem. Do you agree that we should prioritize the fix first?
This is an automated message from the
szha commented on a change in pull request #9790: make array.reshape compatible
with numpy
URL: https://github.com/apache/incubator-mxnet/pull/9790#discussion_r168566530
##
File path: python/mxnet/ndarray/ndarray.py
##
@@ -968,6 +973,14 @@ def reshape(self, shape):
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366020161
The first time a user goes to build something, you can't just throw errors
at him and refuse to build. This discourages use of mxnet. I don't know how
many
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366020161
The first time a user goes to build something, you can;t just throw errors
at him and refuse to build. This discourages use of mxnet. I don;t know how
many
marcoabreu commented on a change in pull request #9799: Cleaned up image
classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#discussion_r168567787
##
File path: KEYS
##
@@ -480,3 +480,40 @@
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r165535818
##
File path: src/operator/nn/activation-inl.h
##
@@ -21,7 +21,7 @@
* Copyright (c) 2015 by
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r165535890
##
File path: src/operator/nn/activation.cc
##
@@ -17,69 +17,130 @@
* under the License.
*/
+
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168570879
##
File path: tests/cpp/include/test_core_op.h
##
@@ -311,68 +339,166 @@ class CoreOpExecutor : public
cjolivier01 commented on issue #9677: Refactor operators and add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#issuecomment-366034644
There's only two out of 10-or-15-or-so tests that are disabled.
I am fine with the merge from the point of the cpp tests, although
zheng-da commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168584501
##
File path: tests/python/gpu/test_gluon_model_zoo_gpu.py
##
@@ -0,0 +1,171 @@
+# Licensed to the Apache
larroy commented on a change in pull request #9799: Cleaned up image
classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#discussion_r168561303
##
File path:
example/image-classification/predict-cpp/image-classification-predict.cc
##
@@
larroy commented on a change in pull request #9799: Cleaned up image
classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#discussion_r168561191
##
File path:
example/image-classification/predict-cpp/image-classification-predict.cc
##
@@
szha commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366013807
See "Guidelines for Reviewers/Committers" in
https://cwiki.apache.org/confluence/display/MXNET/Development+Process
larroy commented on a change in pull request #9799: Cleaned up image
classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#discussion_r168561521
##
File path:
example/image-classification/predict-cpp/image-classification-predict.cc
##
@@
piiswrong commented on a change in pull request #9790: make array.reshape
compatible with numpy
URL: https://github.com/apache/incubator-mxnet/pull/9790#discussion_r168566146
##
File path: python/mxnet/ndarray/ndarray.py
##
@@ -968,6 +973,14 @@ def reshape(self, shape):
szha closed pull request #9777: [MX-9588] Add micro averaging strategy for F1
metric
URL: https://github.com/apache/incubator-mxnet/pull/9777
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
marcoabreu commented on a change in pull request #9799: Cleaned up image
classification cpp example
URL: https://github.com/apache/incubator-mxnet/pull/9799#discussion_r168567571
##
File path: CMakeLists.txt
##
@@ -671,8 +672,7 @@ if(USE_CPP_PACKAGE)
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 d03182f [MX-9588] Add micro
marcoabreu commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168571705
##
File path: tests/cpp/operator/batchnorm_test.cc
##
@@ -335,108 +447,113 @@ class BatchNormValidator
larroy commented on a change in pull request #9677: Refactor operators and add
MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168580246
##
File path: prepare_mkldnn.sh
##
@@ -0,0 +1,114 @@
+#!/bin/bash
+
+# Licensed to the Apache Software
cjolivier01 commented on issue #9798: fix cmake
URL: https://github.com/apache/incubator-mxnet/pull/9798#issuecomment-366033126
cmake doesn't use config.mk. config.mk is for the Makefile, and standard
makefiles are very dumb compared to cmake (ie dont supply a language and
mechanisms for
chsin opened a new issue #9800: Can't run C++ example
URL: https://github.com/apache/incubator-mxnet/issues/9800
## Description
See below.
## Environment info (Required)
I didn't install the python package for this build, but this is the result
from previous builds and should
zheng-da commented on a change in pull request #9677: Refactor operators and
add MKLDNN
URL: https://github.com/apache/incubator-mxnet/pull/9677#discussion_r168584029
##
File path: tests/python/gpu/test_gluon_model_zoo_gpu.py
##
@@ -0,0 +1,171 @@
+# Licensed to the Apache
1 - 100 of 140 matches
Mail list logo