- 22 1月, 2019 1 次提交
-
-
由 nhzlx 提交于
BUG: After continuing to input different data, the output cannot be aligned test=develop
-
- 18 1月, 2019 6 次提交
-
-
由 zhaozhehao 提交于
* refactor tree2col operator with new memory mechanism test=develop * test=develop * test=develop * Modified API according to panyx0718 test=develop * fix API change according to heavengate test=develop * Modify API comment test=develop
-
由 Tao Luo 提交于
test_analyzer_mm_dnn runs in serial
-
由 Tao Luo 提交于
test=develop
-
由 chengduo 提交于
test=develop
-
由 Tao Luo 提交于
add pyramid_dnn c++ inference test
-
由 Yan Chunwei 提交于
-
- 17 1月, 2019 9 次提交
-
-
由 Yiqun Liu 提交于
* Revert the modification of while_op in #14764. test=develop * Remove the dependency of GRPC_DEPS. test=develop
-
由 Yan Chunwei 提交于
-
由 乔龙飞 Qiao Longfei 提交于
gru add origin mode
-
由 gongweibao 提交于
-
由 Tao Luo 提交于
test=develop
-
由 Zhaolong Xing 提交于
fix analysis config bug
-
由 wopeizl 提交于
fix unit test cases
-
由 Yan Chunwei 提交于
-
由 Yan Chunwei 提交于
-
- 16 1月, 2019 12 次提交
-
-
由 Xin Pan 提交于
Fix the exception when tensor format is x
-
由 wopeizl 提交于
disable the parallel mode for adam op on windows test=develop
-
由 Tao Luo 提交于
remove unused doc folder
-
由 Yiqun Liu 提交于
* Simplify the compare op for CPU. * Use asynchronous tensor copy in reshape_op's kernel. * Optimize while_op for test, avoiding creating variables every time. test=develop * Enable the cache of kernel type and kernel function. test=develop * Enable profiling with gperftools. * Remove flags for testing, and fix the linking error. test=develop * Delete the codes of ChooseKernel. test=develop * Fix bug when preparing ExecutorPrepareContext for while_op. * Fix missing depending on grpc libraries. * Remove the redundant print. test=develop * Follow comments. * Remove the codes related to prepare the ExecutorPrepareContext for while_op. test=develop
-
由 tensor-tang 提交于
Enable element_wise_add operator for a ngraph engine
-
由 tensor-tang 提交于
Enable softmax operator for a ngraph engine
-
由 Tao Luo 提交于
test=develop
-
由 nhzlx 提交于
-
由 peizhilin 提交于
-
由 nhzlx 提交于
-
由 Xin Pan 提交于
add imperative mode design
-
由 Xin Pan 提交于
Enhance key generation for Pool INT8 test
-
- 15 1月, 2019 12 次提交
-
-
由 peizhilin 提交于
test=develop
-
由 tensor-tang 提交于
Fuse/second order mul sub and fuse repeated fc relu
-
由 bingyanghuang 提交于
* disable conv3d mkldnn in dam * Add some comments test=develop
-
由 Xin Pan 提交于
expose CompiledProgram
-
由 Xin Pan 提交于
fix deadlink in CONTRIBUTING.md
-
由 Xin Pan 提交于
polish imperative codes
-
由 乔龙飞 Qiao Longfei 提交于
adam support multithread
-
由 Xin Pan 提交于
test=develop
-
由 Xin Pan 提交于
test=develop
-
由 mozga-intel 提交于
test=develop
-
由 liuwei1031 提交于
* fix github issue 15267 test=develop * fix github issue 15267 test=develop
-
由 wopeizl 提交于
add the python callstack for debug support test=develop
-