marcoabreu commented on issue #14519: Fix script retrieval
URL: https://github.com/apache/incubator-mxnet/pull/14519#issuecomment-476486003
FYI, This file is not intended for enduser usage and I'd not recommend
linking it in any documentation.
reminisce opened a new pull request #14521: [numpy] Fix unit tests after using
numpy-compatible shape definition
URL: https://github.com/apache/incubator-mxnet/pull/14521
Fixed several unit tests listed in
https://github.com/apache/incubator-mxnet/issues/14454.
@junrushao1994
reminisce merged pull request #14520: Fix a bug to pass the test in
test_contrib_rnn
URL: https://github.com/apache/incubator-mxnet/pull/14520
This is an automated message from the Apache Git Service.
To respond to the
This is an automated email from the ASF dual-hosted git repository.
reminisce pushed a commit to branch numpy
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/numpy by this push:
new 38f2e06 Fix a bug to pass the test
This is an automated email from the ASF dual-hosted git repository.
lanking 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 a9458ca Fixes for CI downloads
lanking520 merged pull request #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
PistonY closed issue #14514: CUDA 10.1 support
URL: https://github.com/apache/incubator-mxnet/issues/14514
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use
PistonY commented on issue #14514: CUDA 10.1 support
URL:
https://github.com/apache/incubator-mxnet/issues/14514#issuecomment-476440163
OK,I will.
Thanks for your help.
This is an automated message from the Apache Git
haojin2 commented on issue #14514: CUDA 10.1 support
URL:
https://github.com/apache/incubator-mxnet/issues/14514#issuecomment-476440028
@PistonY Please also let us know if you run into problems when building from
source. I actually tried building with CUDA 10.1 + CuDNN 7.5 myself a few
haojin2 commented on issue #14514: CUDA 10.1 support
URL:
https://github.com/apache/incubator-mxnet/issues/14514#issuecomment-476439782
@PistonY Well in short term (like within 2 or 3 days) no, but I'll try to
contact related persons on this issue and hopefully we can provide that in the
PistonY commented on issue #14514: CUDA 10.1 support
URL:
https://github.com/apache/incubator-mxnet/issues/14514#issuecomment-476439313
@vdantu Yes.
@haojin2 Do you have plans to release mxnet-cu101mkl?
If you don't I will build from source.
HaoLiuHust commented on issue #12544: [Precision Problem] about the IRHeader
when using pack and unpack
URL:
https://github.com/apache/incubator-mxnet/issues/12544#issuecomment-476438638
@huyangc yes, I have read the code too, if we want to use it as we want, we
can write a custom pack
zheng-da opened a new pull request #14520: Fix a bug to pass the test in
test_contrib_rnn
URL: https://github.com/apache/incubator-mxnet/pull/14520
## Description ##
Two things are fixed: 1) when converting to NumPy-compatible shape
definition, we shouldn't have the check, 2) fix
HaoLiuHust commented on issue #14499: about the IRHeader when using pack and
unpack
URL:
https://github.com/apache/incubator-mxnet/issues/14499#issuecomment-476438496
yes, I have read it too, if we want to use it as we want, we can write a
custom pack and unpack
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 a506e77 Bump the publish
pengzhao-intel commented on issue #14173: [WIP] MXNet AMP (automatic mixed
precision)
URL: https://github.com/apache/incubator-mxnet/pull/14173#issuecomment-476435228
> We tested all (except for the newest pose estimation) of the networks from
GluonCV and for all of them we saw between
pengzhao-intel commented on issue #14496: performance degradation from 1.3.1 to
1.4.0
URL:
https://github.com/apache/incubator-mxnet/issues/14496#issuecomment-476430815
@sun-dev The performance issue talked in this issue is NOT related to
MKLDNN. We have verified the performance of
vandanavk commented on issue #14519: Fix script retrieval
URL: https://github.com/apache/incubator-mxnet/pull/14519#issuecomment-476420044
@mxnet-label-bot update [Java, Doc, pr-awaiting-merge]
This is an automated message
seujung commented on issue #13735: update wavenet codes
URL: https://github.com/apache/incubator-mxnet/pull/13735#issuecomment-476419732
@abhinavs95 the latest comment is
https://github.com/apache/incubator-mxnet/pull/13735/commits/ee24721f4a6474ebb26f6ffd19da6ebbb31cf5fd.
Apply the
vandanavk commented on issue #14519: Fix script retrieval
URL: https://github.com/apache/incubator-mxnet/pull/14519#issuecomment-476417097
@mxnet-label-bot add [Java, Doc, pr-awaiting-review]
This is an automated message from
vandanavk opened a new pull request #14519: Fix script retrieval
URL: https://github.com/apache/incubator-mxnet/pull/14519
## Description ##
Existing instructions retrieves a html file instead of .sh
```
wget
abhinavs95 edited a comment on issue #13735: update wavenet codes
URL: https://github.com/apache/incubator-mxnet/pull/13735#issuecomment-476415628
@seujung could you please address the latest comments?
@ThomasDelteil Could you please check if your comments are addressed?
abhinavs95 commented on issue #13735: update wavenet codes
URL: https://github.com/apache/incubator-mxnet/pull/13735#issuecomment-476415628
@seujung could you please address the latest comments?
This is an automated message
yuxihu commented on issue #14480: Tidy up storage allocation and deallocation
URL: https://github.com/apache/incubator-mxnet/pull/14480#issuecomment-476414431
@mxnet-label-bot update [pr-awaiting-review]
This is an automated
yuxihu edited a comment on issue #14480: Tidy up storage allocation and
deallocation
URL: https://github.com/apache/incubator-mxnet/pull/14480#issuecomment-475438810
@eric-haibin-lin @apeforest @anirudh2290 Please help review. It looks like
CI is unstable. The failure is not related to
eric-haibin-lin opened a new pull request #14518: [BUGFIX] fix shape ndim
out-of-bound bug
URL: https://github.com/apache/incubator-mxnet/pull/14518
## Description ##
Fix a bug in the iterator which is uncovered by the numpy branch. It used to
cause undefined behavior in memory. No new
ptrendx commented on issue #14173: [WIP] MXNet AMP (automatic mixed precision)
URL: https://github.com/apache/incubator-mxnet/pull/14173#issuecomment-476408792
> Sharing for sharing the speedup results. Are those benchmarked with
multiple GPUs with kvstore?
There are multiple
abhinavs95 commented on issue #14380: fix type mismatch bugs
URL: https://github.com/apache/incubator-mxnet/pull/14380#issuecomment-476406618
@stereomatchingkiss Could you please close this PR if your issue is already
fixed? Thanks!
ptrendx commented on a change in pull request #14173: [WIP] MXNet AMP
(automatic mixed precision)
URL: https://github.com/apache/incubator-mxnet/pull/14173#discussion_r268881846
##
File path: python/mxnet/amp/amp.py
##
@@ -0,0 +1,262 @@
+# Licensed to the Apache Software
ptrendx commented on a change in pull request #14173: [WIP] MXNet AMP
(automatic mixed precision)
URL: https://github.com/apache/incubator-mxnet/pull/14173#discussion_r268881270
##
File path: python/mxnet/amp/loss_scaler.py
##
@@ -0,0 +1,77 @@
+# Licensed to the Apache
ptrendx commented on a change in pull request #14173: [WIP] MXNet AMP
(automatic mixed precision)
URL: https://github.com/apache/incubator-mxnet/pull/14173#discussion_r268881105
##
File path: python/mxnet/amp/loss_scaler.py
##
@@ -0,0 +1,77 @@
+# Licensed to the Apache
ptrendx commented on a change in pull request #14173: [WIP] MXNet AMP
(automatic mixed precision)
URL: https://github.com/apache/incubator-mxnet/pull/14173#discussion_r268879746
##
File path: python/mxnet/amp/lists/symbol.py
##
@@ -0,0 +1,175 @@
+# Licensed to the Apache
gavinmbell commented on issue #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#issuecomment-476397435
There are two download() functions here. Can we put that download function
in a library type of script and then use it accordingly - to adhere to a
lebeg commented on a change in pull request #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#discussion_r268859815
##
File path: cpp-package/example/get_data.sh
##
@@ -14,29 +16,48 @@
# KIND, either express or implied. See the
haojin2 commented on issue #14445: Speedup SequenceMask on GPU
URL: https://github.com/apache/incubator-mxnet/pull/14445#issuecomment-476374579
@eric-haibin-lin please check
This is an automated message from the Apache Git
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 e8142c4 Bump the publish
haojin2 commented on issue #14514: CUDA 10.1 support
URL:
https://github.com/apache/incubator-mxnet/issues/14514#issuecomment-476367026
I think the problem is that MXNet is looking for CUDA 10.0: `OSError:
libcudart.so.10.0: cannot open shared object file: No such file or directory`
ShownX commented on issue #14459: Cannot release memory sometimes
URL:
https://github.com/apache/incubator-mxnet/issues/14459#issuecomment-476365390
What is persistance mode? How can I avoid this mode?
This is an automated
vdantu commented on issue #14508: python import models include mxnet cause a
segmentation error
URL:
https://github.com/apache/incubator-mxnet/issues/14508#issuecomment-476353735
@beingjoey : Could you please elaborate what fixed this issue? Did you just
remove the
```
from
cjolivier01 commented on issue #14304: error: inlining failed in call to
always_inline 'float _cvtsh_ss(short unsigned int)': target specific option
mismatch
URL:
https://github.com/apache/incubator-mxnet/issues/14304#issuecomment-476352680
+1
vdantu commented on issue #14514: CUDA 10.1 support
URL:
https://github.com/apache/incubator-mxnet/issues/14514#issuecomment-476352484
@mxnet-label-bot add [CUDA, Question]
@PistonY : Is CUDA in your LD_LIBRARY_PATH?
```
export LD_LIBRARY_PATH=:$LD_LIBRARY_PATH
```
vdantu commented on issue #14517: Build from source, clojure, lein test
erroring out
URL:
https://github.com/apache/incubator-mxnet/issues/14517#issuecomment-476351040
@mxnet-label-bot add [Clojure, Test]
This is an
Chouffe opened a new issue #14517: Build from source, clojure, lein test
erroring out
URL: https://github.com/apache/incubator-mxnet/issues/14517
## Description
When building MXNet from source and running `lein test` using the locally
built jar, it errors out with a lot of
mxnet-label-bot commented on issue #14517: Build from source, clojure, lein
test erroring out
URL:
https://github.com/apache/incubator-mxnet/issues/14517#issuecomment-476342975
Hey, this is the MXNet Label Bot.
Thank you for submitting the issue! I will try and suggest some labels so
abhinavs95 commented on issue #14513: [WIP] Update base CUDA image for CI to
v10.0
URL: https://github.com/apache/incubator-mxnet/pull/14513#issuecomment-476341244
@mxnet-label-bot add[pr-work-in-progress, Test, CI]
This is
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 a6cbbe5 Bump the publish
lanking520 commented on a change in pull request #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#discussion_r268801291
##
File path: cpp-package/example/get_data.sh
##
@@ -14,29 +16,48 @@
# KIND, either express or implied. See the
nswamy commented on a change in pull request #14503: API to create RecordIO
files
URL: https://github.com/apache/incubator-mxnet/pull/14503#discussion_r268789368
##
File path: python/mxnet/io/io.py
##
@@ -966,6 +985,165 @@ def creator(*args, **kwargs):
This is an automated email from the ASF dual-hosted git repository.
nswamy pushed a commit to branch fit-api
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/fit-api by this push:
new 8186772 [MXNet-1349][Fit API]Add
nswamy merged pull request #14442: [MXNet-1349][Fit API]Add validation support
and unit tests for fit() API
URL: https://github.com/apache/incubator-mxnet/pull/14442
This is an automated message from the Apache Git Service.
lanking520 commented on a change in pull request #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#discussion_r268781218
##
File path: tools/dependencies/make_shared_dependencies.sh
##
@@ -20,11 +20,37 @@
# This is a convenience
lebeg commented on issue #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#issuecomment-476313672
> These still have references to that data.dmlc.ml broken link
>
> `tools/coreml/README.md`
>
> `example/rcnn/README.md`
>
>
lebeg commented on issue #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#issuecomment-476311611
> The `-L` option is specified in the template by `—local`.
@lanking520 Sorry, I think I caused some confusion, I meant the `--location`
option. I
lebeg edited a comment on issue #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#issuecomment-476311611
> The `-L` option is specified in the template by `—local`.
@lanking520 Sorry, I think I caused some confusion, I meant the `--location`
wangpichao commented on issue #9667: [Feature request] += operator for Symbol
URL:
https://github.com/apache/incubator-mxnet/issues/9667#issuecomment-476302337
@MaAo @dongzhuoyao please change the a=+b to a = a + b, and it would fix
the issue.
junrushao1994 commented on issue #14342: Ensure all usage of `ndim` to be 0-d
tensor compatible
URL:
https://github.com/apache/incubator-mxnet/issues/14342#issuecomment-476291976
Going to act on this thread this week. I guess most of them have been
addressed in recent PRs like #14361,
RuRo commented on issue #9712: two consecutive backward cause error Check
failed: type_ != nullptr The any container is empty requested
URL:
https://github.com/apache/incubator-mxnet/issues/9712#issuecomment-476291190
Can confirm,
```python
for loss in losses:
loss.backward()
kohillyang edited a comment 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-476283396
And, there seem many functions to load parameters from a pre-trained file,
but for nn.Block, there is no public way
kohillyang 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-476283396
And, there seem many functions to load parameters from a pre-trained file,
but for nn.Block, there is no public way to
ptrendx commented on issue #14489: global shuffling
URL:
https://github.com/apache/incubator-mxnet/issues/14489#issuecomment-476282674
Please do. Did you confirm that you get global shuffling with
ImageRecordIter with index provided?
kohillyang edited a comment 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-476279328
I think currently CustomOp may need to be redesigned, they cannot be
executed in multi-threads, and even in
kohillyang 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-476279328
I think currently CustomOp may need to be redesigned, there cannot be
executed in multi-threads, and even in
sun-dev commented on issue #14496: performance degradation from 1.3.1 to 1.4.0
URL:
https://github.com/apache/incubator-mxnet/issues/14496#issuecomment-476279184
Just to clarify, for the data type change from 32bit to 64bit, we're talking
about the tensor shape data type, not the actual
wkcn commented on issue #14515: Should gluon layer support **name** field?
URL:
https://github.com/apache/incubator-mxnet/issues/14515#issuecomment-476275526
+1. I think it is necessary to support custom name for gluon block.
For example, to implement a ResNet model, I would like to
wkcn commented on issue #14512: the inference speed using C++ API with mxnet of
higher version is slower than lower mxnet
URL:
https://github.com/apache/incubator-mxnet/issues/14512#issuecomment-476272939
@IvyGongoogle Could you please provide the forward time between different
versions
grez72 commented on issue #14489: global shuffling
URL:
https://github.com/apache/incubator-mxnet/issues/14489#issuecomment-476251485
I can confirm that ```ImageRecordIter``` only returns zeros for the index
values. Should I submit a separate issue for this?
perdasilva edited a comment on issue #14502: [Test Failure] GPU Test failures
across different CUDA versions
URL:
https://github.com/apache/incubator-mxnet/issues/14502#issuecomment-476122806
Created a PR (#14513) updating CI to use CUDA v10.0 and use the
CUDNN_VERSION environment
perdasilva edited a comment on issue #14502: [Test Failure] GPU Test failures
across different CUDA versions
URL:
https://github.com/apache/incubator-mxnet/issues/14502#issuecomment-476113911
Perhaps the reason CI isn't reporting any issues is that both the version of
cudnn in the
xrmzju commented on issue #14516: cann't achive linear speed up with multi GPUs
URL:
https://github.com/apache/incubator-mxnet/issues/14516#issuecomment-476212093
@mxnet-label-bot add [Performance]
This is an automated
lebeg commented on issue #14493: Updated documentation about nightly tests
URL: https://github.com/apache/incubator-mxnet/pull/14493#issuecomment-476196910
@aaronmarkham
This is an automated message from the Apache Git
lebeg closed pull request #14495: [WIP] DO NOT MERGE
URL: https://github.com/apache/incubator-mxnet/pull/14495
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
mxnet-label-bot commented on issue #14516: cann't achive linear speed up with
multi GPUs
URL:
https://github.com/apache/incubator-mxnet/issues/14516#issuecomment-476191699
Hey, this is the MXNet Label Bot.
Thank you for submitting the issue! I will try and suggest some labels so
IvyGongoogle commented on issue #14512: the inference speed using C++ API with
mxnet of higher version is slower than lower mxnet
URL:
https://github.com/apache/incubator-mxnet/issues/14512#issuecomment-476192973
@wkcn sorry, I can not find some C++ codes about how to use profiler.
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 fc6966b Bump the publish
xrmzju opened a new issue #14516: cann't achive linear speed up with multi GPUs
URL: https://github.com/apache/incubator-mxnet/issues/14516
Note: Providing complete information in the most concise form is the best
way to get help. This issue template serves as the checklist for essential
yangfly opened a new issue #14515: Should gluon layer support **name** field?
URL: https://github.com/apache/incubator-mxnet/issues/14515
At present, the **name** of **Gluon** layer is automatically extended to
`xxx/operator0_fwd`, based on `name_scope`, which embodies modularization and
mxnet-label-bot commented on issue #14515: Should gluon layer support **name**
field?
URL:
https://github.com/apache/incubator-mxnet/issues/14515#issuecomment-476182047
Hey, this is the MXNet Label Bot.
Thank you for submitting the issue! I will try and suggest some labels so
that
wkcn commented on issue #14512: the inference speed with mxnet of higher
version is slower than lower mxnet
URL:
https://github.com/apache/incubator-mxnet/issues/14512#issuecomment-476167976
@IvyGongoogle Could you please use the profiler to measure the execution
time?
wkcn edited a comment on issue #14512: the inference speed with mxnet of higher
version is slower than lower mxnet
URL:
https://github.com/apache/incubator-mxnet/issues/14512#issuecomment-476167976
@IvyGongoogle Could you please use the profiler to measure the execution
time?
smissan commented on issue #14116: Failure in generated op.h in version 1.3.1
URL:
https://github.com/apache/incubator-mxnet/issues/14116#issuecomment-476167933
No
On Mon., Mar. 25, 2019, 8:56 a.m. bj5546, wrote:
> was this bug fixed?
>
> —
> You are receiving this
bj5546 commented on issue #14116: Failure in generated op.h in version 1.3.1
URL:
https://github.com/apache/incubator-mxnet/issues/14116#issuecomment-476165049
was this bug fixed?
This is an automated message from the Apache
mika-fischer commented on issue #13460: onnx export slope for prelu operator
corrected
URL: https://github.com/apache/incubator-mxnet/pull/13460#issuecomment-476145791
@Roshrini: Is there a successor to this PR? As it seems, currently exporting
to ONNX with PReLu is still broken, right?
PistonY opened a new issue #14514: CUDA 10.1 support
URL: https://github.com/apache/incubator-mxnet/issues/14514
I use CUDA 10.1 with mxnet-cu100mkl
But I got this issus
```
Traceback (most recent call last):
File "/home/piston/PycharmProjects/NASNet-gluon/model/nasnet.py",
lobanov-m commented on issue #13226: [MXNet-1211] Factor and "Like" modes in
BilinearResize2D operator
URL: https://github.com/apache/incubator-mxnet/pull/13226#issuecomment-476144487
Built failed because of
```
test_model.R:129: error: Fine-tune
cannot open URL
mxnet-label-bot commented on issue #14514: CUDA 10.1 support
URL:
https://github.com/apache/incubator-mxnet/issues/14514#issuecomment-476142366
Hey, this is the MXNet Label Bot.
Thank you for submitting the issue! I will try and suggest some labels so
that the appropriate MXNet
ymjiang edited a comment on issue #14485: Any suggestion to accelerate
parameter update on PS for distributed training?
URL:
https://github.com/apache/incubator-mxnet/issues/14485#issuecomment-476124225
Ping @eric-haibin-lin @szha for help
lebeg commented on issue #14513: [WIP] Update base CUDA image for CI to v9.2
URL: https://github.com/apache/incubator-mxnet/pull/14513#issuecomment-476128263
I can suggest to try to update to 10 instead, like here:
https://github.com/apache/incubator-mxnet/pull/12850
ymjiang commented on issue #14485: Any suggestion to accelerate parameter
update on PS for distributed training?
URL:
https://github.com/apache/incubator-mxnet/issues/14485#issuecomment-476124225
Ping @eric-haibin-lin
This
ymjiang edited a comment on issue #14485: Any suggestion to accelerate
parameter update on PS for distributed training?
URL:
https://github.com/apache/incubator-mxnet/issues/14485#issuecomment-476124225
Ping @eric-haibin-lin @szha
perdasilva commented on issue #14502: [Test Failure] GPU Test failures across
different CUDA versions
URL:
https://github.com/apache/incubator-mxnet/issues/14502#issuecomment-476122806
Created a PR #14513 to see if I can catch this issue in CI
perdasilva opened a new pull request #14513: [WIP] Update base CUDA image for CI
URL: https://github.com/apache/incubator-mxnet/pull/14513
## Description ##
I believe, due to cudnn version, some tests are not being run in CI and
therefore some bugs are being let through.
This
perdasilva commented on issue #14502: [Test Failure] GPU Test failures across
different CUDA versions
URL:
https://github.com/apache/incubator-mxnet/issues/14502#issuecomment-476113911
Perhaps the reason CI isn't reporting any issues is that both the lower
version of cudnn in the
lebeg edited a comment on issue #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#issuecomment-476109350
> Might be -s. Please put the environment variable into
`make_shared_dependeices.sh`
`-s` is for 'silent' and is the exact reason why CI is
lebeg commented on issue #14507: model links data.dmlc.ml are broken
URL:
https://github.com/apache/incubator-mxnet/issues/14507#issuecomment-476108911
I'm working on the fixes here:
https://github.com/apache/incubator-mxnet/pull/14504
lebeg commented on issue #14504: Fixes for CI downloads
URL: https://github.com/apache/incubator-mxnet/pull/14504#issuecomment-476109350
> Might be -s. Please put the environment variable into
`make_shared_dependeices.sh`
`-s` is for 'silent' and is the exact reason why CI is not
fe-codes commented on issue #13482: [Feature Request] Release gpu memory by API.
URL:
https://github.com/apache/incubator-mxnet/issues/13482#issuecomment-476104061
+1
This is an automated message from the Apache Git Service.
IvyGongoogle commented on issue #14512: the inference speed with mxnet of
higher version is slower than lower mxnet
URL:
https://github.com/apache/incubator-mxnet/issues/14512#issuecomment-476101136
@wkcn I dont know which op in my model is slower in newer mxnet. no dilated
convolutional
IvyGongoogle commented on issue #13928: MXNet 1.5.0 is slower than 1.3.0 when
intputs are variant
URL:
https://github.com/apache/incubator-mxnet/issues/13928#issuecomment-476099058
@wkcn no dilated convolutional layers in my model which is a ocr recognition
model with cnn and rnn
IvyGongoogle edited a comment on issue #13928: MXNet 1.5.0 is slower than 1.3.0
when intputs are variant
URL:
https://github.com/apache/incubator-mxnet/issues/13928#issuecomment-476099058
@wkcn no dilated convolutional layers in my model which is a ocr recognition
model with simple cnn
beingjoey commented on issue #14508: python import models include mxnet cause a
segmentation error
URL:
https://github.com/apache/incubator-mxnet/issues/14508#issuecomment-476098498
Now I covered this problem by removing skimage transform model. But I am
still worried about that.
1 - 100 of 117 matches
Mail list logo