- 20 9月, 2018 7 次提交
-
-
由 Zeng Jinle 提交于
Fix sparse Adam and Gradient clip of SelectedRows
-
由 Tao Luo 提交于
* refine analyzer_nlp_tester * refine analyzer_rnn/vis_tester
-
由 Tao Luo 提交于
add readme of /doc
-
由 sneaxiy 提交于
-
由 Yihua Xu 提交于
* Optimize GRU with AVX instruction * Clean code * Add the Unitest and fix the align issue * Remove the remanent part of the unitest part * Code clean * Fix the parameters length issue for fusion_gru to pass CI * Change the default type as float32
-
由 chengduo 提交于
* Add Preface * Add demo code * Save file * Refine code * seems can work * use elementwise strategy * Use ElementwiseComputeEx * Add comments * extract functions from operator * Refine code * Follow comment * code refine * add op_fuse pass * add backward * code refine * use TopologySortOperations * follow comments * refine IsFusible * code enhance * fix op_fusion_pass * refine code * refine fuse_elemwise_act_op * adjust the input and output * refine logic * add intermediate_edge * disable inplace * follow comments * refine logic * follow comments * Remove the removable IntermediateOut * change strategy * code refine * enable fuse backward * code refine * code refine * rename unit test * follow comments
-
由 Tao Luo 提交于
update mklml version
-
- 19 9月, 2018 33 次提交
-
-
由 qingqing01 提交于
-
由 tensor-tang 提交于
-
由 Xin Pan 提交于
Delete develop doc/fluid folder
-
由 Qingsheng Li 提交于
Sequence Scatter Op
-
由 Xin Pan 提交于
To support full model saving.
-
由 Jiabin Yang 提交于
fix mac unittest 279/395 error without distribute
-
由 Yan Xu 提交于
move uci_housing dataset to bce
-
由 Tao Luo 提交于
hidden InferenceTranspiler
-
由 Xin Pan 提交于
avoid creating dangling ir::Node.
-
由 Xin Pan 提交于
In the future, we'd like to encourage user to save everything during training. This allows us to 1. Do more flexible optimization passes 2. Re-train and fune-tune
-
由 Jiabin Yang 提交于
-
由 Jiabin Yang 提交于
fix mac unitest on ci
-
由 Jiabin Yang 提交于
fix mac compile error
-
由 JiabinYang 提交于
-
由 Yancey1989 提交于
-
由 tink2123 提交于
-
由 Wu Yi 提交于
fix py2 matplotlib deps
-
由 Xin Pan 提交于
clean unused inference_optimize c++ implementation
-
由 luotao1 提交于
-
由 chengduo 提交于
* add unit test for nested drnn * add nested dyn_rnn * refine while_op * fix bug
-
由 whs 提交于
* Add truncated gaussian initializer. * Fix unitest. * Update API.spec * Fix code style and fix bug. * Fix code style. * Small fix.
-
由 Xin Pan 提交于
Node should be created by Graph::CreateXXX so that they are managed by graph.
-
由 Zeng Jinle 提交于
Modify some ops to save memory
-
由 JiabinYang 提交于
-
由 Yu Yang 提交于
Wait input when data transform
-
由 whs 提交于
* Add python api for expand op. * Fix unitest. * Remove 'out' from arguments and fix code style. * fix API.spec * Fix API * Fix unitest
-
由 Jiabin Yang 提交于
-
由 Jiabin Yang 提交于
-
由 Dun 提交于
* loosen the restriction of output_size in conv2d_transpose * test and docs * fix code style * fix ci test error * bug fix * fix python3 issue
-
由 typhoonzero 提交于
-
由 JiabinYang 提交于
-
由 Yu Yang 提交于
fix memory optimize
-
由 qingqing01 提交于
-