- 19 12月, 2019 14 次提交
-
-
由 juncaipeng 提交于
-
由 Chengmo 提交于
* test=develop, speed dense calc & communication
-
由 Wojciech Uss 提交于
test=develop
-
由 GaoWei8 提交于
* Remove self-set accuracy parameters of op tests: max_relative_error test=develop * fix error test=develop
-
由 GaoWei8 提交于
* Remove self-set accuracy parameters of op tests: max_relative_erro test=develop * fix error test=develop
-
由 songyouwei 提交于
* add Linear layer test=develop * update unittest for coverage test=develop
-
由 GaoWei8 提交于
* Remove self-set accuracy parameters of op tests:atol test=develop * keep smaller parameters test=develop * fix error test=develop
-
由 juncaipeng 提交于
* fix post training quantization bug of memory constrained, support the input be different, test=develop
-
由 Zeng Jinle 提交于
* add some debug flags to auto growth allocator, test=develop * add comments about auto growth, test=develop
-
由 Leo Chen 提交于
-
由 guofei 提交于
1. Make while_op accept GPU conditional data 2. Add more complex test cases for while_loop API
-
由 GaoWei8 提交于
test=develop
-
由 GaoWei8 提交于
* Remove self-set accuracy parameters of op tests: max_relative_error test=develop * fix errors test=develop
-
由 silingtong123 提交于
-
- 18 12月, 2019 9 次提交
-
-
由 juncaipeng 提交于
*use dtype to determine whether check_grade is needed, and delete useless class
-
由 Huihuang Zheng 提交于
The fixed bugs: 1. The condition sub-graph is not pruned 2. When backward graph is extremely simple, the whole backward ops are pruned.
-
由 GaoWei8 提交于
test=develop
-
由 juncaipeng 提交于
-
由 Zeng Jinle 提交于
-
由 juncaipeng 提交于
-
由 Leo Chen 提交于
adds unary operator __neg__ for VarBase in dygraph mode, and for Variable in static graph mode.
-
由 GaoWei8 提交于
* Remove self-set accuracy parameters of op tests: max_relative_error test=develop * Remove self-set accuracy parameters of op tests: max_relative_error test=develop * Remove self-set parameters of op tests: max_relative_error test=develop
-
由 GaoWei8 提交于
* Remove self-set accuracy parameters of op tests: max_relative_error test=develop * Remove self-set accuracy parameters of op tests test=develop * keep smaller parameters test=develop
-
- 17 12月, 2019 8 次提交
-
-
由 zhouwei25 提交于
* increase example code of py_func, fix some wrong description of English API doc
-
由 Youwei Song 提交于
test=develop
-
由 Zhang Ting 提交于
-
由 Huihuang Zheng 提交于
-
由 GaoWei8 提交于
* Remove self-set accuracy parameters of op tests test=develop * add cast test=develop * Remove self-set accuracy parameters of op tests:atol test=develop * lrn_ngraph_op test=develop * Keep smaller parameters test=develop
-
由 GaoWei8 提交于
-
由 Youwei Song 提交于
* remove build_once & name_scope (Conv2D) test=develop * fix unittest test=develop * Conv2DTranspose * Conv3D & Conv3DTranspose test=develop * Pool2D & BatchNorm * Embedding * LayerNorm * GRUUnit & NCE * PRelu * BilinearTensorProduct * GroupNorm & SpectralNorm * TreeConv test=develop * fix LayerNorm in transformer unnittest test=develop * disable LayerNorm or BatchNorm in multicard test=develop * refine Layer.create_parameter api test=develop * refine LayerNorm, remove begin_norm_axis param, add normed shape check test=develop * LayerNorm bug fix test=develop
-
由 WangXi 提交于
-
- 16 12月, 2019 9 次提交
-
-
由 zhaoyuchen2018 提交于
* Fix softmax cuda bug * Refine multihead log and softmax logic
-
由 Kaipeng Deng 提交于
* yolo_box OP add Attr(clip_bbox). test=develop
-
由 zhupengyang 提交于
- ngarph: elementwise_sub, elementwise_mul - mkldnn: transpose, sum - others: scatter_nd test=develop
-
由 GaoWei8 提交于
test=develop
-
由 zhouwei25 提交于
-
由 Leo Chen 提交于
* fix elementwise_pow bug on integer, test=develop * use llrint to support elementwise_pow_grad, test=develop * add some tests, test=develop * revert grad functor, test=develop
-
由 Chen Weihang 提交于
-
由 Leo Chen 提交于
* patch math method for varbase using auto-generated op functions, test=develop * clean code that handles batch_size, test=develop * follow comments, test=develop * follow comments, test=develop * code clean, test=develop
-
由 lilong12 提交于
-