- 25 Dec, 2018 3 commits
-
-
Jared Roesch committed
-
* add ssd ops to mxnet.py * add ssd ops to mxnet.py * add result check for multibox and nms unit tests * add result check for multibox and nms unit tests * address @kevinthesun's comments * Disable cuda test for nms for now.
Zhi committed -
typo "@func myfunc" => "func @myfunc"
Liang ZOU committed
-
- 24 Dec, 2018 7 commits
-
-
Dominic Symes committed
-
eqy committed
-
Steven S. Lyubomirsky committed
-
Wuwei Lin committed
-
Steven S. Lyubomirsky committed
-
masahi committed
-
Dtype of output of pad should follows input, but if dtype of input is not float, output will still be float becase pad_value is float.
lixiaoquan committed
-
- 22 Dec, 2018 1 commit
-
-
Jared Roesch committed
-
- 21 Dec, 2018 1 commit
-
-
Haichen Shen committed
-
- 20 Dec, 2018 5 commits
-
-
* Add MXNet test example for relay * Fix a bug in BiasAddSimplifier
Haichen Shen committed -
* Add Eddie to committer * Fix order
Haichen Shen committed -
Zhi committed
-
Sergei Grechanik committed
-
masahi committed
-
- 19 Dec, 2018 2 commits
-
-
Jian Weng committed
-
Andrew Tulloch committed
-
- 18 Dec, 2018 5 commits
-
-
Yong Wu committed
-
* [PASS] Avoid recursion in FoldScaleAxis * remove GetForwardScale
Tianqi Chen committed -
Zhi committed
-
Sam Skalicky committed
-
Jared Roesch committed
-
- 17 Dec, 2018 1 commit
-
-
ziheng committed
-
- 15 Dec, 2018 1 commit
-
-
Siva committed
-
- 14 Dec, 2018 4 commits
-
-
[TOPI] NCHWc added input shape 4 condition, intel graphics conv2d schedule debugged for inception_v3 workloads (#2265)
Leyuan Wang committed -
Lianmin Zheng committed
-
OKA Naoya committed
-
Wei Chen committed
-
- 13 Dec, 2018 3 commits
-
-
Alexey Romanov committed
-
Jian Weng committed
-
typo: Xlinx => Xilinx
Liang ZOU committed
-
- 12 Dec, 2018 5 commits
-
-
Wuwei Lin committed
-
Siva committed
-
* fix a issue when running with graph_runtime_debug in python; * add support to `debug_get_output` in python; * comply with the linter;
Liangfu Chen committed -
Siju committed
-
Wei Chen committed
-
- 11 Dec, 2018 2 commits
-
-
Doesn't make sense to have %1 = mul(%x, %y) computed but never use the result %1
Sean committed -
Ruslan Baratov committed
-