- 02 4月, 2019 2 次提交
-
-
由 Wojciech Uss 提交于
-
由 lidanqing 提交于
* fix preprocess script with processbar, integrity check and logs test=develop * delete unnecessary empty lines, change function name test=develop
-
- 01 4月, 2019 1 次提交
-
-
由 Tao Luo 提交于
test=develop
-
- 29 3月, 2019 4 次提交
-
-
由 Shixiaowei02 提交于
-
由 Wojciech Uss 提交于
test=develop
-
由 Shixiaowei02 提交于
-
由 lidanqing 提交于
test=develop
-
- 28 3月, 2019 10 次提交
-
-
由 nhzlx 提交于
refine trt first run add quant dequant fuse pass omit simplify_anakin_priorbox_detection template omit transpose_flatten_concat_fuse template test=develop
-
由 lidanqing 提交于
test=develop
-
由 lidanqing 提交于
test=develop
-
由 lidanqing 提交于
test=develop
-
由 chengduo 提交于
* modify the interface of Pass::Allay test=develop * Polish code test=develop * Fix Travis CI test=develop * fix Pass::Apply interface test=develop * Fix Travis CI test=develop
-
由 Sylwester Fraczek 提交于
test=develop
-
由 gongweibao 提交于
-
由 Sylwester Fraczek 提交于
test=develop
-
由 Michał Gallus 提交于
* Refine default MKL-DNN Pass order test=develop * Add comment to default MKL-DNN Pass list test=develop
-
由 Wojciech Uss 提交于
* C-API quantization core test=develop Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com> * Decouple Quantizer from AnalysisPredictor test=develop * fixes after review test=develop * renamed mkldnn quantize stuff test=develop * remove ifdef from header file test=develop
-
- 27 3月, 2019 1 次提交
-
-
由 Yihua Xu 提交于
* Disable compare for accuracy issue. test=develop * Add todo comments to show more information. test=develop
-
- 26 3月, 2019 1 次提交
-
-
由 nhzlx 提交于
test=develop
-
- 25 3月, 2019 2 次提交
-
-
由 liuwei1031 提交于
* fix cdn issue, test=develop * fix cdn issue, test=develop
-
由 Wojciech Uss 提交于
test=develop
-
- 22 3月, 2019 1 次提交
-
-
由 nhzlx 提交于
2. refine trt code test=develop
-
- 21 3月, 2019 1 次提交
-
-
由 Wojciech Uss 提交于
* Add enabling quantization test=develop * remove unused (here) function
-
- 20 3月, 2019 13 次提交
-
-
由 nhzlx 提交于
1. refine anakin engine 2. add data type for zero copy align dev branch and PaddlePaddle:feature/anakin-engine brach the cudnn workspace modify was not included for now, because we use a hard code way in feature/anakin-engine branch. There should be a better way to implement it, and subsequent submissions will be made. test=develop
-
由 nhzlx 提交于
-
由 nhzlx 提交于
-
由 nhzlx 提交于
-
由 nhzlx 提交于
-
由 nhzlx 提交于
support change input size
-
由 nhzlx 提交于
-
由 flame 提交于
* use anakin batch norm and scale implement fluid batch norm
-
由 flame 提交于
cherry-pick feature/anakin-engine: add anakin softmax/transpose/batch_norm/flatten/reshape op (#16020) * add anakin softmax/ flatten/reshape/transpose/batch_norm op converter
-
由 nhzlx 提交于
-
由 nhzlx 提交于
-
由 flame 提交于
* add activation op * test conv2d relu sigmoid tanh
-
由 Yan Chunwei 提交于
-
- 19 3月, 2019 4 次提交
-
-
由 luotao1 提交于
test=develop
-
由 zhhsplendid 提交于
test=develop
-
由 Tao Luo 提交于
-
由 Jacek Czaja 提交于
* - Fix to crash of Transformer when mkldnn is to be used Desc: TensorCopy was not setting MKLDNN primitive descriptor when layout was to be kMKLDNN test=develop * - Enable transformer for mkl-dnn test=develo * - Compilation fix test=develop * - Removed manual selection of MKL-DNN ops to be used in Transformer test test=develop
-