- 06 11月, 2019 7 次提交
-
-
由 juncaipeng 提交于
* add channel_wise_dequantized_max_abs op and ChannelWiseDequantOpFuser, test=develop
-
由 xiebaiyuan 提交于
optimise conv 1x1 ... ,test=develop (#2388)
-
由 Wilber 提交于
update reshape op to support multiple input types of shape. priority: input(ShapeTensor) > input(Shape) > attr(shape) update slice op to support multiple iput types of starts and ends. priority: input(StartsTensor) > input(StartsTensorList) > attr(starts)
-
由 Wilber 提交于
fill_constant kernel only registered float type, only the float data type is produced, which is obviously a bug. Now, produce data based on the data type attr. By the way, fix the cast kernel bug.
-
由 huzhiqiang 提交于
-
由 sangoly 提交于
-
由 TianXiaogang 提交于
* fix: fix omp thread bug * fix: fix compile android level & test=develop * fix: fix omp bug * fix: fix omp bug test=develop
-
- 05 11月, 2019 4 次提交
-
-
由 zhupengyang 提交于
test=develop
-
由 sangoly 提交于
-
由 lijianshe02 提交于
* fix step rnn model run bugs test=develop
-
- 04 11月, 2019 3 次提交
-
-
由 xiebaiyuan 提交于
-
由 huzhiqiang 提交于
* move some basic ops into extra type to reduce library size test=develop (#2347)
-
由 Zhaolong Xing 提交于
test=develop
-
- 02 11月, 2019 1 次提交
-
-
由 xiebaiyuan 提交于
* add mem opt option for high api ,test = develop * fix is_lod params && test-performance ,test=develop * fix useless init emptyimage , test = develop
-
- 01 11月, 2019 10 次提交
-
-
由 juncaipeng 提交于
-
由 zhupengyang 提交于
* [XPU] add batchnorm op bridge and unit test test=develop * fix DMLC_USE_GLOG test=develop
-
由 Yanzhan Yang 提交于
* delete remaining opencl headers test=develop * checkout specific commit for opencl headers test=develop
-
由 Yanzhan Yang 提交于
* add opencl headers by git clone test=develop * add opencl headers by git clone test=develop
-
由 liu zhengxi 提交于
-
由 huzhiqiang 提交于
fix buf: model_optimize_tool can not compile preperly on mac environment (#2326)
-
由 xiebaiyuan 提交于
* add mem opt option for high api ,test = develop * fix is_lod params && test-performance ,test=develop
-
由 石晓伟 提交于
-
由 TianXiaogang 提交于
-
由 huzhiqiang 提交于
* fix model_opt_tool bug : judge WITH_MKL to choose whether to compile MKL test=develop
-
- 31 10月, 2019 5 次提交
-
-
由 Yuan Shuai 提交于
* Fix conv bn bug. test=develop * Fix bug in pattern_matcher. test=develop
-
由 Jiaying Zhao 提交于
* add GPU_CL for test_net_benchmark. * test compile * fix mobile build error
-
由 huzhiqiang 提交于
Fix compiling bug in android_armv7_demo : cxx demo can not compile properly because demo' android version is different from that of library file (#2308) link armv7 demo to android-23 to make sure the demo can compile properly cxx demo can not compile properly because demo' android version is different from that of library file, we fix this bug by linking armv7 demo to android-23
-
由 huzhiqiang 提交于
Add 'inference' folder into build.lite.x86, 'inference' folder contains head files、library files and demo of x86 compiling (#2301) Add inference folder into build.lite.x86, build.lite.x86/inference folder contains head files、library files and demo of x86 compiling
-
由 liu zhengxi 提交于
* alter the unit tests api for googlenet, resnet50, inceptionv4, mobilenetv1, mobilenetv2 and thier corresponding cmake, test=develop * disable checks and correct some incorrect statement, test=develop
-
- 30 10月, 2019 5 次提交
-
-
由 Yuan Shuai 提交于
* [LOG] macro for vlog. test=develop
-
由 zhupengyang 提交于
test=develop
-
由 hong19860320 提交于
-
由 Xiaoyang LI 提交于
-
由 huzhiqiang 提交于
* we can build x86 dynamic library by `build.sh x86`
-
- 29 10月, 2019 5 次提交
-
-
由 huzhiqiang 提交于
remove dynamic library compiling from `ci_build.sh build_test_server`
-
由 Yuan Shuai 提交于
* Fix bug target for kHost and kARM not equal. test=develop * Fix license. test=develop
-
由 guofei 提交于
test=develop
-
由 liu zhengxi 提交于
* add tanh op in x86 platform and its unittest, test=develop * add gelu op on x86 platform and add its unittests, test=develop * update depends for math_function for activation for gelu, test=develop
-
由 zhupengyang 提交于
test=develop
-