PaddlePaddle / Paddle
大约 1 年前同步成功

代码
- 文件
- 提交
- 分支
- Tags
- 贡献者
- 分支图
- Diff
Issue 1423
- 列表
- 看板
- 标记
- 里程碑
合并请求 543
Wiki 0
- Wiki
分析
- 仓库
- DevOps
项目成员
Pages

1.8.0版本，conv_transpose_eltwiseadd_bn_fuse_pass导致PaddleOCR检测模型CPU预测结果错误

#24585 · opened 5月 15, 2020 by saxon_zh Intel
- 已关闭
- 8
更新于6月 11, 2020
What is the condition when padding fc is used in inference

#24523 · opened 5月 14, 2020 by saxon_zh Intel
- 1
更新于9月 16, 2020
Ernie INT8 accuracy drop on 2.0-alpha

#24510 · opened 5月 13, 2020 by saxon_zh Intel int8
- 已关闭
- 3
更新于7月 08, 2020
pvanet model INT8 model accuracy drop 10%

#24461 · opened 5月 13, 2020 by saxon_zh Intel int8
- 6
更新于7月 14, 2020
Ernie INT8 test crash

#24394 · opened 5月 11, 2020 by saxon_zh Intel
- 已关闭
- 4
更新于5月 12, 2020
develop版本，transformer模型CPU-MKLDNN预测速度明显下降

#24373 · opened 5月 09, 2020 by saxon_zh Intel
- 已关闭
- 3
更新于5月 14, 2020
Please add GELU in-place execution support

#24328 · opened 5月 07, 2020 by saxon_zh Intel InterestingIdea
- 1
更新于5月 20, 2020
[oneDNN] Add bfloat16 to C-API

#24295 · opened 4月 30, 2020 by saxon_zh Intel
- 1
更新于7月 15, 2020
Accuracy drop on INT8 Ernie QAT inference

#24052 · opened 4月 21, 2020 by saxon_zh Intel int8
- 已关闭
- 5
更新于5月 28, 2020
[DNNL] Extend elementwise_add kernel to support broadcasting

#23927 · opened 4月 16, 2020 by saxon_zh Intel InterestingIdea
- 已关闭
- 2
更新于6月 04, 2020
PaddleSlim and Paddle inference (Intel cpu) support all common quantized models

#23346 · opened 3月 31, 2020 by saxon_zh v2.0 Intel
- 已关闭
- 5
更新于4月 29, 2020
PR 22961 caused significant performance regression on BERT inference

#23319 · opened 3月 30, 2020 by saxon_zh Intel inference
- 已关闭
- 3
更新于4月 03, 2020
[DNNL] Check for distributing training example and try running on MKL-DNN engine

#23135 · opened 3月 22, 2020 by saxon_zh Intel InterestingIdea
- 0
更新于3月 22, 2020
[DNNL] Evaluate trained paddle models using mkl-dnn kernels

#23134 · opened 3月 22, 2020 by saxon_zh Intel InterestingIdea
- 0
更新于3月 22, 2020
[DNNL] Speedup conv grad DNNL kernel

#23133 · opened 3月 22, 2020 by saxon_zh Intel InterestingIdea
- 0
更新于3月 22, 2020
Develop branch accuracy drop after upgrading to DNNL1.2

#23100 · opened 3月 19, 2020 by saxon_zh Intel
- 已关闭
- 1
更新于7月 15, 2020
[DNNL] Replace sum dnnl op with binary dnnl op in sum op implementation

#23099 · opened 3月 19, 2020 by saxon_zh Intel InterestingIdea
- 已关闭
- 1
更新于4月 04, 2020
How does InplaceInferer works?

#23074 · opened 3月 18, 2020 by saxon_zh Intel question
- 已关闭
- 7
更新于4月 04, 2020
[DNNL] Implement operator softmax with cross entropy

#23073 · opened 3月 18, 2020 by saxon_zh Intel InterestingIdea
- 0
更新于3月 18, 2020
[DNNL] Refactor activation code

#23070 · opened 3月 17, 2020 by saxon_zh Intel
- 2
更新于3月 24, 2020

1
2
3
4
5
6
7
…
17