yajiedesign commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183231272
##
File path: Jenkinsfile
##
@@ -622,6 +663,42 @@ try {
}
}
}
+},
+
marcoabreu commented on a change in pull request #10608: [MXNET-307] Add
tutorial tests to the CI
URL: https://github.com/apache/incubator-mxnet/pull/10608#discussion_r183235012
##
File path: tests/tutorials/test_tutorials.py
##
@@ -0,0 +1,187 @@
+# Licensed to the Apache
marcoabreu commented on a change in pull request #10608: [MXNET-307] Add
tutorial tests to the CI
URL: https://github.com/apache/incubator-mxnet/pull/10608#discussion_r183234953
##
File path: ci/docker/install/ubuntu_scala.sh
##
@@ -23,9 +23,8 @@
set -ex
# install
marcoabreu commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183235359
##
File path: ci/docker/runtime_functions.sh
##
@@ -371,7 +371,6 @@
marcoabreu opened a new pull request #10642: [MXNET-353] Switch to OpenJDK
URL: https://github.com/apache/incubator-mxnet/pull/10642
## Description ##
This PR switches the used packages from Oracle JDK to OpenJDK since the
oracle download seems to be failing
## Checklist ##
marcoabreu commented on issue #10624: [MXNET-351] Fix a bug in the MKLDNN
integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#issuecomment-383378772
I think you're missing the ```mx_cmake_mkldnn_lib``` argument in unpack_lib
ThomasDelteil commented on issue #10638: [Feature Request] Gluon model zoo
allow fine-tuning
URL:
https://github.com/apache/incubator-mxnet/issues/10638#issuecomment-383358379
Also @szha , I think another common use case is to use a network as a
featurizer. Currently the only way I found
luoyetx commented on issue #10544: name_scope/prefix doesn't work
URL:
https://github.com/apache/incubator-mxnet/issues/10544#issuecomment-383358915
parameters of `SymbolBlock` is not saved.
```python
import mxnet as mx
from mxnet import gluon as gl, nd
from mxnet.gluon
haojin2 opened a new pull request #10639: [MXNET-350] Logical NOT Operator
URL: https://github.com/apache/incubator-mxnet/pull/10639
## Description ##
Implementation for logical NOT operator
## Checklist ##
### Essentials ###
- [x] The PR title starts with [MXNET-350]
-
haojin2 commented on a change in pull request #10639: [MXNET-350] Logical NOT
Operator
URL: https://github.com/apache/incubator-mxnet/pull/10639#discussion_r183227825
##
File path: tests/python/unittest/test_operator.py
##
@@ -2095,14 +2111,14 @@ def test_dot():
zheng-da commented on issue #10624: [MXNET-351] Fix a bug in the MKLDNN
integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#issuecomment-383366624
@marcoabreu do you know why CI doesn't unpack the right package?
I'm trying to unpack cmake_mkldnn_gpu and it seems the
leedstark opened a new issue #10640: Mxnet cu90 on Windows
URL: https://github.com/apache/incubator-mxnet/issues/10640
## Description
I've installed Mxnet using pip install mxnet-cu90, when I import the package
it doesn't get recognized.
## Environment info
Windows 64 bit
chinakook commented on issue #10634: How to get internal output with C++ API?
URL:
https://github.com/apache/incubator-mxnet/issues/10634#issuecomment-383368141
``` int device_type = 1;
int device_id = 0;
const char *input_keys[1];
input_keys[0] = "data";
szha commented on issue #10638: [Feature Request] Gluon model zoo allow
fine-tuning
URL:
https://github.com/apache/incubator-mxnet/issues/10638#issuecomment-383357918
The semantics of such call might be ambiguous. Given that we already
consistently name the network parts as "features"
ThomasDelteil commented on issue #10628: [MXNET-342] Fix the multi worker
Dataloader
URL: https://github.com/apache/incubator-mxnet/pull/10628#issuecomment-383357995
It would behave the same way if the dataset relies on reading the file at
run-time.
To make it clearer, instead of
szha commented on issue #10638: [Feature Request] Gluon model zoo allow
fine-tuning
URL:
https://github.com/apache/incubator-mxnet/issues/10638#issuecomment-383357918
The semantics of such call might be ambiguous. Given that we already
consistently name the network parts as "features"
szha commented on issue #10638: [Feature Request] Gluon model zoo allow
fine-tuning
URL:
https://github.com/apache/incubator-mxnet/issues/10638#issuecomment-383359131
In the proposed design, without the knowledge of actual implementation, the
call may either be interpreted as "get me a
ThomasDelteil commented on issue #10638: [Feature Request] Gluon model zoo
allow fine-tuning
URL:
https://github.com/apache/incubator-mxnet/issues/10638#issuecomment-383358167
I agree that documenting the structure of the network would be very helpful
to start with. And also documenting
zheng-da commented on issue #10280: Flaky test_operator.test_correlation
URL:
https://github.com/apache/incubator-mxnet/issues/10280#issuecomment-383364115
Here as well.
http://jenkins.mxnet-ci.amazon-ml.com/blue/organizations/jenkins/incubator-mxnet/detail/PR-10624/7/pipeline
zheng-da commented on issue #10280: Flaky test_operator.test_correlation
URL:
https://github.com/apache/incubator-mxnet/issues/10280#issuecomment-383364134
It seems this one can be reproduced by certain seeds
This is an
zheng-da commented on issue #10624: [MXNET-351] Fix a bug in the MKLDNN
integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#issuecomment-383366624
@marcoabreu do you know why CI doesn't unpack the right package?
I'm trying to unpack cmake_mkldnn_gpu and it seems the
simonmaurer opened a new issue #10641: How to implement custom loss functions
without label assignments (unsupervised) ?
URL: https://github.com/apache/incubator-mxnet/issues/10641
@pengwangucla @saicoco that example
[https://github.com/apache/incubator-mxnet/issues/5580](url) helped me
ThomasDelteil commented on issue #10638: [Feature Request] Gluon model zoo
allow fine-tuning
URL:
https://github.com/apache/incubator-mxnet/issues/10638#issuecomment-383358167
I agree that documenting the structure of the network would be very helpful
to start with. And also documenting
zheng-da commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183229091
##
File path: Jenkinsfile
##
@@ -622,6 +663,42 @@ try {
}
}
}
+},
+
ThomasDelteil commented on issue #10642: [MXNET-353] Switch to OpenJDK
URL: https://github.com/apache/incubator-mxnet/pull/10642#issuecomment-383399351
This PR already has this change, I hope to have it merged tomorrow. Might be
better to wait this one out since the updated images have
piiswrong commented on issue #10637: [MXNET-352] Document behavior of
mx.initializer.Constant
URL: https://github.com/apache/incubator-mxnet/pull/10637#issuecomment-383413272
Gluon specific tutorial shouldn't be put here.
piiswrong commented on issue #10637: [MXNET-352] Document behavior of
mx.initializer.Constant
URL: https://github.com/apache/incubator-mxnet/pull/10637#issuecomment-383413272
Gluon specific tutorial shouldn't be put here. In gluon it's more convenient
to use set_data.
haojin2 opened a new pull request #10645: [MXNET-354] Support elemwise_add/sub
between dense and row sparse tensors
URL: https://github.com/apache/incubator-mxnet/pull/10645
## Description ##
Elemwise_add/sub between dense and row sparse tensors.
## Checklist ##
### Essentials
zheng-da commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183247997
##
File path: tests/cpp/operator/mkldnn.cc
##
@@ -28,6 +28,8 @@
#include
zheng-da commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183247972
##
File path: src/operator/nn/mkldnn/mkldnn_base.cc
##
@@ -25,6 +25,11 @@
namespace
haojin2 commented on issue #10643: [MXNET-355] fix race condition in csr
cast_storage block kernel
URL: https://github.com/apache/incubator-mxnet/pull/10643#issuecomment-383420174
LGTM!
This is an automated message from the
sl1pkn07 commented on issue #10644: Build: error: argument of type "const void
*" is incompatible with parameter of type "const X*"
URL:
https://github.com/apache/incubator-mxnet/issues/10644#issuecomment-383422383
tested with:
cmake 3.11.0
ninja 1.8.2
openblas 0.2.20
eric-haibin-lin opened a new pull request #10643: [WIP] fix race condition in
csr cast_storage block kernel
URL: https://github.com/apache/incubator-mxnet/pull/10643
## Description ##
(Brief description on what this PR is about)
## Checklist ##
### Essentials ###
Please
ThomasDelteil commented on issue #10637: [MXNET-352] Document behavior of
mx.initializer.Constant
URL: https://github.com/apache/incubator-mxnet/pull/10637#issuecomment-383414699
There are several `module` API specific examples in this file, I can switch
the example to a module one if you
marcoabreu commented on issue #10642: [MXNET-353] Switch to OpenJDK
URL: https://github.com/apache/incubator-mxnet/pull/10642#issuecomment-383404710
I'd like to keep this upgrade separate from the other PRs in order to have
the possibility of an easy revert
sl1pkn07 opened a new issue #10644: Build: error: argument of type "const void
*" is incompatible with parameter of type "const X*"
URL: https://github.com/apache/incubator-mxnet/issues/10644
Tried install mxnet througth AUR on my Archlinux
sl1pkn07 commented on issue #10644: Build: error: argument of type "const void
*" is incompatible with parameter of type "const X*"
URL:
https://github.com/apache/incubator-mxnet/issues/10644#issuecomment-383422383
tested with Cmake 3.11.0
```
cmake ../incubator-mxnet \
zheng-da commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183248080
##
File path: src/ndarray/ndarray.cc
##
@@ -495,24 +495,41 @@ const mkldnn::memory
marcoabreu commented on a change in pull request #10624: [MXNET-351] Fix a bug
in the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183250514
##
File path: tests/cpp/operator/mkldnn.cc
##
@@ -28,6 +28,8 @@
#include
eric-haibin-lin commented on issue #10643: [MXNET-355] fix race condition in
csr cast_storage block kernel
URL: https://github.com/apache/incubator-mxnet/pull/10643#issuecomment-383419457
@haojin2 @reminisce
This is an
eric-haibin-lin commented on a change in pull request #10371: [MXNET-263]
Support for dot(dns, csr) = dns and dot(dns, csr.T) = dns on GPU
URL: https://github.com/apache/incubator-mxnet/pull/10371#discussion_r182915535
##
File path: src/operator/tensor/dot-inl.cuh
##
@@
eric-haibin-lin commented on a change in pull request #10371: [MXNET-263]
Support for dot(dns, csr) = dns and dot(dns, csr.T) = dns on GPU
URL: https://github.com/apache/incubator-mxnet/pull/10371#discussion_r183262040
##
File path: src/operator/tensor/dot-inl.h
##
@@
eric-haibin-lin commented on a change in pull request #10371: [MXNET-263]
Support for dot(dns, csr) = dns and dot(dns, csr.T) = dns on GPU
URL: https://github.com/apache/incubator-mxnet/pull/10371#discussion_r183261461
##
File path: tests/python/unittest/test_sparse_operator.py
juliusshufan opened a new pull request #10646: Correctly set the device context
to CPU at symbolic mode when --gpus not set
URL: https://github.com/apache/incubator-mxnet/pull/10646
## Description ##
This PR fixes an issue on example/gluon/image_classification.py
When using argument
KeyKy commented on issue #7450: reporting bugs: pbegin_ <= pend_. Two thread
conflicts.
URL:
https://github.com/apache/incubator-mxnet/issues/7450#issuecomment-383437032
I also get the error in 1.2.0.
```
INFO:root:Epoch[0] Batch [220] Speed: 103.34 samples/sec
DYG111 commented on issue #10626: Could you help build windows pypi package
mxnet-cu90 for version 1.0.0 and version 1.1.0?
URL:
https://github.com/apache/incubator-mxnet/issues/10626#issuecomment-383437168
Sorry, I can't find mxnet-cu90 1.0.0 for windows, please give me a link,
thank
KeyKy commented on issue #7450: reporting bugs: pbegin_ <= pend_. Two thread
conflicts.
URL:
https://github.com/apache/incubator-mxnet/issues/7450#issuecomment-383437032
I also get the error.
```
INFO:root:Epoch[0] Batch [220] Speed: 103.34 samples/sec
accuracy=0.001563
zheng-da commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183279895
##
File path: tests/cpp/operator/mkldnn.cc
##
@@ -28,6 +28,8 @@
#include
eric-haibin-lin commented on issue #10366: fix bug in sgd
URL: https://github.com/apache/incubator-mxnet/pull/10366#issuecomment-383462666
@solin319 how much performance difference did you see if you remove temp
resource?
ThomasDelteil commented on issue #10608: [MXNET-307] Add tutorial tests to the
CI
URL: https://github.com/apache/incubator-mxnet/pull/10608#issuecomment-383399407
@indhub could you have a look at the updated tutorials as per @marcoabreu
comment?
piiswrong commented on a change in pull request #10623: [MXNET-339] Add warning
on input data for RNN for layout NTC
URL: https://github.com/apache/incubator-mxnet/pull/10623#discussion_r183252053
##
File path: python/mxnet/gluon/rnn/rnn_layer.py
##
@@ -286,6 +286,9 @@
piiswrong commented on a change in pull request #10623: [MXNET-339] Add warning
on input data for RNN for layout NTC
URL: https://github.com/apache/incubator-mxnet/pull/10623#discussion_r183252053
##
File path: python/mxnet/gluon/rnn/rnn_layer.py
##
@@ -286,6 +286,9 @@
eric-haibin-lin commented on a change in pull request #10645: [MXNET-354]
Support elemwise_add/sub between dense and row sparse tensors
URL: https://github.com/apache/incubator-mxnet/pull/10645#discussion_r183262382
##
File path: src/operator/tensor/elemwise_binary_op-inl.h
chinakook commented on issue #10644: Build: error: argument of type "const void
*" is incompatible with parameter of type "const X*"
URL:
https://github.com/apache/incubator-mxnet/issues/10644#issuecomment-383446623
#10558
juliusshufan opened a new issue #10647: The gluon example fails to run on CPU
at "symbolic" mode
URL: https://github.com/apache/incubator-mxnet/issues/10647
## Description
When using argument --mode symbolic and not set --gpus, it assumed the
script will run on CPU, while actually the
sl1pkn07 commented on issue #10644: Build: error: argument of type "const void
*" is incompatible with parameter of type "const X*"
URL:
https://github.com/apache/incubator-mxnet/issues/10644#issuecomment-383422383
tested with:
cmake 3.11.0
ninja 1.8.2
openblas 0.2.20
yajiedesign commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183258396
##
File path: Jenkinsfile
##
@@ -311,7 +311,7 @@ try {
bat """mkdir build_vc14_gpu
casscw opened a new issue #10648: Why examlpe wide_deep runs faster on
win10(cpu) than linux(gpu-Tesla M40 24GB)
URL: https://github.com/apache/incubator-mxnet/issues/10648
## Description
code link is here
https://github.com/apache/incubator-mxnet/tree/master/example/sparse/wide_deep
yajiedesign commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183258272
##
File path: cmake/MklDnn.cmake
##
@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation
yajiedesign commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183258295
##
File path: Jenkinsfile
##
@@ -622,6 +663,42 @@ try {
}
}
}
+},
+
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183240802
##
File path: python/mxnet/contrib/quantization.py
##
@@ -72,7 +72,7 @@ def
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183240784
##
File path: include/mxnet/c_api.h
##
@@ -1409,13 +1409,17 @@ MXNET_DLL int
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183240942
##
File path: src/c_api/c_api_symbolic.cc
##
@@ -595,7 +596,12 @@ int
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241827
##
File path: src/operator/quantization/quantize_graph_pass.cc
##
@@ -250,6 +250,165
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241566
##
File path: src/operator/quantization/mkldnn/mkldnn_quantized_pooling.cc
##
@@
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241525
##
File path: src/operator/quantization/mkldnn/mkldnn_quantized_pooling.cc
##
@@
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183240995
##
File path: src/operator/quantization/mkldnn/mkldnn_dequantize-inl.h
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241106
##
File path: src/operator/quantization/mkldnn/mkldnn_quantize-inl.h
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241649
##
File path: src/operator/quantization/mkldnn/mkldnn_requantize-inl.h
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241805
##
File path: src/operator/quantization/quantize_graph_pass.cc
##
@@ -198,7 +198,7
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241376
##
File path: src/operator/quantization/mkldnn/mkldnn_quantized_conv.cc
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241122
##
File path: src/operator/quantization/mkldnn/mkldnn_quantize-inl.h
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183240951
##
File path: src/operator/nn/mkldnn/mkldnn_base.cc
##
@@ -211,6 +211,7 @@
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241596
##
File path: src/operator/quantization/mkldnn/mkldnn_requantize-inl.h
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241614
##
File path: src/operator/quantization/mkldnn/mkldnn_requantize-inl.h
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241662
##
File path: src/operator/quantization/quantize_graph_pass.cc
##
@@ -129,7 +129,7
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241679
##
File path: src/operator/quantization/quantize_graph_pass.cc
##
@@ -159,7 +159,7
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241068
##
File path: src/operator/quantization/mkldnn/mkldnn_dequantize-inl.h
##
@@ -0,0
jinhuang415 commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183241432
##
File path: src/operator/quantization/mkldnn/mkldnn_quantized_pooling.cc
##
@@
marcoabreu commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183235611
##
File path: cmake/MklDnn.cmake
##
@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation
marcoabreu commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183235642
##
File path: cmake/MklDnn.cmake
##
@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation
marcoabreu commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183235548
##
File path: Jenkinsfile
##
@@ -311,7 +311,7 @@ try {
bat """mkdir build_vc14_gpu
vsooda commented on issue #9060: Remove defunct demo
URL: https://github.com/apache/incubator-mxnet/pull/9060#issuecomment-354058923
@piiswrong @simoncorstonoliver I had make this work in February. what is
the problem you must remove this example. just because you could not let it
work?
marcoabreu commented on issue #10629: [MXNET-343]fix Mkldnn with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#issuecomment-383378902
@yajiedesign in future, please start using meaningful commit messages or
amend your commit. The current style does not add any value to
marcoabreu commented on a change in pull request #10629: [MXNET-343]fix Mkldnn
with msvc
URL: https://github.com/apache/incubator-mxnet/pull/10629#discussion_r183235469
##
File path: Jenkinsfile
##
@@ -622,6 +663,42 @@ try {
}
}
}
+},
+
marcoabreu commented on issue #10586: Cannot build ubuntu_gpu CI docker image
(java8 sdk missing)
URL:
https://github.com/apache/incubator-mxnet/issues/10586#issuecomment-383379274
https://github.com/apache/incubator-mxnet/pull/10642
xinyu-intel commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183236474
##
File path: ci/docker/runtime_functions.sh
##
@@ -371,7 +371,6 @@
TaoLv commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183238040
##
File path: src/operator/nn/mkldnn/mkldnn_base.cc
##
@@ -25,6 +25,11 @@
namespace
TaoLv commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183238225
##
File path: tests/cpp/operator/mkldnn.cc
##
@@ -28,6 +28,8 @@
#include "gtest/gtest.h"
TaoLv commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183237445
##
File path: src/ndarray/ndarray.cc
##
@@ -495,24 +495,41 @@ const mkldnn::memory
TaoLv commented on a change in pull request #10624: [MXNET-351] Fix a bug in
the MKLDNN integration.
URL: https://github.com/apache/incubator-mxnet/pull/10624#discussion_r183238519
##
File path: tests/cpp/operator/mkldnn.cc
##
@@ -84,4 +86,250 @@ TEST(MKLDNN_UTIL_FUNC,
91 matches
Mail list logo