GitBox |
[GitHub] [incubator-mxnet] access2rohit commented on a change in pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 19:41 |
GitBox |
[GitHub] [incubator-mxnet] access2rohit commented on a change in pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 19:42 |
GitBox |
[GitHub] [incubator-mxnet] access2rohit commented on a change in pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 19:42 |
GitBox |
[GitHub] [incubator-mxnet] access2rohit commented on a change in pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 19:43 |
GitBox |
[GitHub] [incubator-mxnet] access2rohit commented on a change in pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 19:44 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on pull request #18904: [RFC] MXNet external operators |
Tue, 18 Aug, 19:45 |
GitBox |
[GitHub] [incubator-mxnet] Zha0q1 commented on pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 20:09 |
GitBox |
[GitHub] [incubator-mxnet] Zha0q1 edited a comment on pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 20:28 |
GitBox |
[GitHub] [incubator-mxnet] Zha0q1 edited a comment on pull request #18932: Numpy Ops Large Tensor Tests |
Tue, 18 Aug, 20:29 |
GitBox |
[GitHub] [incubator-mxnet] eric-haibin-lin opened a new issue #18957: MKLDNN headers missing in mxnet mac nightly build |
Tue, 18 Aug, 20:32 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on issue #18957: MKLDNN headers missing in mxnet mac nightly build |
Tue, 18 Aug, 20:32 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on issue #18951: [RFC] GPU performance improvements in MXNet engine |
Tue, 18 Aug, 20:51 |
GitBox |
[GitHub] [incubator-mxnet] DickJC123 commented on pull request #18905: Fix setting cudnn bias stride and change order of bgrad and wgrad to boost performance |
Tue, 18 Aug, 21:02 |
GitBox |
[GitHub] [incubator-mxnet] ptrendx commented on pull request #18905: Fix setting cudnn bias stride and change order of bgrad and wgrad to boost performance |
Tue, 18 Aug, 21:20 |
GitBox |
[GitHub] [incubator-mxnet] Zha0q1 commented on pull request #18925: Numpy Dot Large Tensor Fix |
Tue, 18 Aug, 21:23 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18925: Numpy Dot Large Tensor Fix |
Tue, 18 Aug, 21:24 |
GitBox |
[GitHub] [incubator-mxnet] ptrendx commented on issue #18951: [RFC] GPU performance improvements in MXNet engine |
Tue, 18 Aug, 21:40 |
GitBox |
[GitHub] [incubator-mxnet] HahTK commented on a change in pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 21:43 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 21:45 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 21:46 |
GitBox |
[GitHub] [incubator-mxnet] HahTK commented on a change in pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 21:49 |
GitBox |
[GitHub] [incubator-mxnet] b-shi commented on issue #17980: When compiled with MKL, fully_connected calls DNNL while dot and batch_dot call MKL |
Tue, 18 Aug, 21:52 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 21:52 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 21:53 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 22:00 |
GitBox |
[GitHub] [incubator-mxnet] DickJC123 merged pull request #18905: Fix setting cudnn bias stride and change order of bgrad and wgrad to boost performance |
Tue, 18 Aug, 22:16 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18916: [1.x] Backporting TensorRT-Gluon Partition API (and TensorRT 7 support) |
Tue, 18 Aug, 22:22 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18916: [1.x] Backporting TensorRT-Gluon Partition API (and TensorRT 7 support) |
Tue, 18 Aug, 22:25 |
GitBox |
[GitHub] [incubator-mxnet] mseth10 commented on a change in pull request #18916: [1.x] Backporting TensorRT-Gluon Partition API (and TensorRT 7 support) |
Tue, 18 Aug, 22:25 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18916: [1.x] Backporting TensorRT-Gluon Partition API (and TensorRT 7 support) |
Tue, 18 Aug, 22:26 |
GitBox |
[GitHub] [incubator-mxnet] mseth10 commented on a change in pull request #18916: [1.x] Backporting TensorRT-Gluon Partition API (and TensorRT 7 support) |
Tue, 18 Aug, 22:28 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18958: Fix Horovod build error due to missing exported symbols |
Tue, 18 Aug, 22:30 |
GitBox |
[GitHub] [incubator-mxnet] leezu opened a new pull request #18958: Fix Horovod build error due to missing exported symbols |
Tue, 18 Aug, 22:30 |
GitBox |
[GitHub] [incubator-mxnet] Kh4L commented on a change in pull request #18916: [1.x] Backporting TensorRT-Gluon Partition API (and TensorRT 7 support) |
Tue, 18 Aug, 22:37 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky merged pull request #18894: [1.x] Backporting #18779 to v1.x |
Tue, 18 Aug, 22:50 |
GitBox |
[GitHub] [incubator-mxnet] mseth10 commented on a change in pull request #18690: [WIP] optimize graph in presence of dynamic shape ops |
Tue, 18 Aug, 23:04 |
GitBox |
[GitHub] [incubator-mxnet] waytrue17 commented on a change in pull request #18690: [WIP] optimize graph in presence of dynamic shape ops |
Tue, 18 Aug, 23:08 |
GitBox |
[GitHub] [incubator-mxnet] heaseny commented on pull request #18289: avoid skipping validation stage when data read iterator exists |
Tue, 18 Aug, 23:12 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18959: Get rid of monkey patching in LossScaler overflow handling |
Tue, 18 Aug, 23:56 |
GitBox |
[GitHub] [incubator-mxnet] mk-61 opened a new pull request #18959: Get rid of monkey patching in LossScaler overflow handling |
Tue, 18 Aug, 23:56 |
GitBox |
[GitHub] [incubator-mxnet] Zha0q1 commented on pull request #18925: Numpy Dot Large Tensor Fix |
Wed, 19 Aug, 00:07 |
GitBox |
[GitHub] [incubator-mxnet] davisliang commented on issue #16167: [RFC] Apache MXNet 2.0 Roadmap |
Wed, 19 Aug, 00:32 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on issue #16167: [RFC] Apache MXNet 2.0 Roadmap |
Wed, 19 Aug, 00:36 |
GitBox |
[GitHub] [incubator-mxnet] sandeep-krishnamurthy merged pull request #18925: Numpy Dot Large Tensor Fix |
Wed, 19 Aug, 00:36 |
GitBox |
[GitHub] [incubator-mxnet] Zha0q1 commented on pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 01:09 |
GitBox |
[GitHub] [incubator-mxnet] leezu commented on pull request #18958: Fix Horovod build error due to missing exported symbols |
Wed, 19 Aug, 01:48 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18958: Fix Horovod build error due to missing exported symbols |
Wed, 19 Aug, 01:48 |
GitBox |
[GitHub] [incubator-mxnet] Light-- commented on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 01:55 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 01:55 |
GitBox |
[GitHub] [incubator-mxnet] wkcn commented on pull request #18910: [v1.x] backport remove upper bound (#18857) |
Wed, 19 Aug, 02:13 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18910: [v1.x] backport remove upper bound (#18857) |
Wed, 19 Aug, 02:14 |
GitBox |
[GitHub] [incubator-mxnet] mk-61 commented on pull request #18959: Get rid of monkey patching in LossScaler overflow handling |
Wed, 19 Aug, 02:50 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18959: Get rid of monkey patching in LossScaler overflow handling |
Wed, 19 Aug, 02:50 |
GitBox |
[GitHub] [incubator-mxnet] AIGirl10 commented on issue #14589: convert from mxnet to onnx failed, with Unrecognized attribute: spatial for operator BatchNormalization |
Wed, 19 Aug, 03:37 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 03:59 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 04:04 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 04:12 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on a change in pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 04:13 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 04:21 |
GitBox |
[GitHub] [incubator-mxnet] szha merged pull request #18910: [v1.x] backport remove upper bound (#18857) |
Wed, 19 Aug, 04:45 |
GitBox |
[GitHub] [incubator-mxnet] ptrendx commented on a change in pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 04:53 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on a change in pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 04:59 |
GitBox |
[GitHub] [incubator-mxnet] cybaj opened a new issue #18960: Dockerfile build with mxnet dependency package no gpus detected |
Wed, 19 Aug, 05:15 |
GitBox |
[GitHub] [incubator-mxnet] github-actions[bot] commented on issue #18960: Dockerfile build with mxnet dependency package no gpus detected |
Wed, 19 Aug, 05:17 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on issue #18960: Dockerfile build with mxnet dependency package no gpus detected |
Wed, 19 Aug, 05:26 |
GitBox |
[GitHub] [incubator-mxnet] szha opened a new pull request #18961: turn on MXNET_SAFE_ACCUMULATION by default |
Wed, 19 Aug, 05:33 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18961: turn on MXNET_SAFE_ACCUMULATION by default |
Wed, 19 Aug, 05:33 |
GitBox |
[GitHub] [incubator-mxnet] Light-- commented on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 06:17 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 06:27 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 06:28 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 06:30 |
GitBox |
[GitHub] [incubator-mxnet] Light-- commented on issue #17258: mxnet.base.MXNetError: [12:37:13] src/executor/../common/exec_utils.h:391: InferShape pass cannot decide shapes for the following arguments |
Wed, 19 Aug, 06:37 |
GitBox |
[GitHub] [incubator-mxnet] szha opened a new issue #18962: tutorial didn't mention how to disable hybridization |
Wed, 19 Aug, 06:43 |
GitBox |
[GitHub] [incubator-mxnet] ikeliou closed issue #18901: The same model with different weights has different inference speeds. |
Wed, 19 Aug, 06:48 |
GitBox |
[GitHub] [incubator-mxnet] ikeliou commented on issue #18901: The same model with different weights has different inference speeds. |
Wed, 19 Aug, 06:48 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky merged pull request #18916: [1.x] Backporting TensorRT-Gluon Partition API (and TensorRT 7 support) |
Wed, 19 Aug, 07:22 |
GitBox |
[GitHub] [incubator-mxnet] Light-- commented on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 07:26 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 07:27 |
GitBox |
[GitHub] [incubator-mxnet] Light-- commented on issue #3539: can anyone give an example of using set_lr_mult |
Wed, 19 Aug, 07:28 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 07:29 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 07:29 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 07:30 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 07:31 |
GitBox |
[GitHub] [incubator-mxnet] szha commented on issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file? |
Wed, 19 Aug, 07:32 |
GitBox |
[GitHub] [incubator-mxnet] Light-- commented on issue #15718: set lr_mult, wd_mult of var , it didn't work |
Wed, 19 Aug, 07:34 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #15718: set lr_mult, wd_mult of var , it didn't work |
Wed, 19 Aug, 07:34 |
GitBox |
[GitHub] [incubator-mxnet] Light-- commented on issue #9101: how to get the lr_mult parameter of a symbol |
Wed, 19 Aug, 07:35 |
GitBox |
[GitHub] [incubator-mxnet] samskalicky commented on pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 08:41 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #15718: set lr_mult, wd_mult of var , it didn't work |
Wed, 19 Aug, 09:11 |
GitBox |
[GitHub] [incubator-mxnet] xiaoFine commented on issue #18415: error: unknown type name 'uint32_t' |
Wed, 19 Aug, 09:12 |
GitBox |
[GitHub] [incubator-mxnet] Light-- edited a comment on issue #15718: set lr_mult, wd_mult of var , it didn't work |
Wed, 19 Aug, 09:16 |
GitBox |
[GitHub] [incubator-mxnet] marcoabreu commented on pull request #18904: [RFC] MXNet external operators |
Wed, 19 Aug, 11:22 |
GitBox |
[GitHub] [incubator-mxnet] cybaj commented on issue #18960: Dockerfile build with mxnet dependency package no gpus detected |
Wed, 19 Aug, 11:48 |
GitBox |
[GitHub] [incubator-mxnet] pengzhao-intel commented on issue #18954: Ensure when USE_BLAS=mkl at mxnet build doesn't break with MKL_USE_ILP64=ON |
Wed, 19 Aug, 13:32 |
GitBox |
[GitHub] [incubator-mxnet] Masquerade0097 commented on issue #18415: error: unknown type name 'uint32_t' |
Wed, 19 Aug, 13:49 |
GitBox |
[GitHub] [incubator-mxnet] anko-intel commented on issue #18954: Ensure when USE_BLAS=mkl at mxnet build doesn't break with MKL_USE_ILP64=ON |
Wed, 19 Aug, 13:58 |
GitBox |
[GitHub] [incubator-mxnet] mk-61 commented on pull request #18959: Get rid of monkey patching in LossScaler overflow handling |
Wed, 19 Aug, 14:42 |
GitBox |
[GitHub] [incubator-mxnet] mxnet-bot commented on pull request #18959: Get rid of monkey patching in LossScaler overflow handling |
Wed, 19 Aug, 14:42 |
GitBox |
[GitHub] [incubator-mxnet] TaoLv commented on issue #17980: When compiled with MKL, fully_connected calls DNNL while dot and batch_dot call MKL |
Wed, 19 Aug, 15:49 |
GitBox |
[GitHub] [incubator-mxnet] eric-haibin-lin merged pull request #18958: Fix Horovod build error due to missing exported symbols |
Wed, 19 Aug, 16:16 |