合并请求 · PaddlePaddle / Paddle

更改 cross_entropy2 和 grad 名字与其它OP一致

!19157 · opened 8月 13, 2019 by saxon_zh Intel NGraph
- 已关闭
- 3
更新于9月 08, 2019
Update ngraph engine for multiple threading

!19155 · opened 8月 13, 2019 by saxon_zh Intel NGraph
- 已合并
- 7
更新于8月 28, 2019
Use sparse matrix to implement FusedEmbeddingSeqPoolGradKernel

!19153 · opened 8月 12, 2019 by saxon_zh Intel
- 已合并
- 6
更新于8月 22, 2019
Add generalized Conv+Activation MKLDNN fuse pass creation Part1

!19072 · opened 8月 08, 2019 by saxon_zh Intel
- 已合并
- 5
更新于8月 15, 2019
Use sparse matrix to implement fused emb_seq_pool operator

!19064 · opened 8月 08, 2019 by saxon_zh Intel
- 已合并
- 21
更新于8月 20, 2019
UT coverage for guassian_mkldnn_op and batch_norm_mkldnn_op

!19011 · opened 8月 05, 2019 by saxon_zh Intel
- 已合并
- 1
更新于8月 13, 2019
Replace Relu with bounded Relu in MobileNetV2 quantization mkldnn

!18988 · opened 8月 02, 2019 by saxon_zh Intel int8
- 已合并
- 1
更新于8月 12, 2019
Add support for new QAT models

!18970 · opened 8月 01, 2019 by saxon_zh Intel int8
- 已合并
- 51
更新于9月 25, 2019
Fix mAP problem in unit test of int8 object detection test

!18946 · opened 7月 31, 2019 by saxon_zh Intel int8
- 已合并
- 9
更新于8月 15, 2019
Add generalized Conv+Activation MKLDNN fuse pass creation

!18942 · opened 7月 31, 2019 by saxon_zh Code Cleanup Intel enhancement inference
- 已关闭
- 11
更新于8月 21, 2019
[MKL-DNN] Removing transfering X from FWD to GRAD via device context

!18911 · opened 7月 30, 2019 by saxon_zh Code Cleanup Intel concurrency
- 已合并
- 5
更新于8月 01, 2019
Add conv dequant squash

!18905 · opened 7月 30, 2019 by saxon_zh Intel int8
- 已合并
- 12
更新于8月 27, 2019
Revert "use static variable to do cache instead of thread local in thread frequent switching case

!18879 · opened 7月 29, 2019 by saxon_zh Intel
- 已合并
- 0
更新于7月 30, 2019
Add Conv+LeakyReLU MKLDNN fuse pass

!18875 · opened 7月 29, 2019 by saxon_zh Intel
- 已关闭
- 12
更新于7月 31, 2019
upgrade ngraph version and simplify ngraph engine

!18853 · opened 7月 27, 2019 by saxon_zh Intel NGraph
- 已合并
- 0
更新于7月 31, 2019
fix mul_mkldnn_op build failure

!18816 · opened 7月 25, 2019 by saxon_zh Intel
- 已合并
- 2
更新于7月 26, 2019
remove unused TransposeINT8MKLDNNOpKernel for higher UT coverage

!18791 · opened 7月 24, 2019 by saxon_zh Code Cleanup Intel
- 已合并
- 2
更新于7月 26, 2019
Add LeakyReLU MKLDNN support

!18762 · opened 7月 23, 2019 by saxon_zh Intel performance tuning
- 已合并
- 20
更新于7月 26, 2019
[MKL-DNN] Fix to int8 performance regression (#18698)

!18758 · opened 7月 23, 2019 by saxon_zh Intel inference int8 performance tuning
- 已合并
- 18
更新于7月 30, 2019
change ComputeINT8 to template version to remove checking dst_datatype code

!18756 · opened 7月 23, 2019 by saxon_zh Intel int8
- 已合并
- 4
更新于10月 28, 2019

PaddlePaddle / Paddle 大约 1 年 前同步成功

PaddlePaddle / Paddle
大约 1 年前同步成功