Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
兽拳
Paddle
提交
fd49ebcb
P
Paddle
项目概览
兽拳
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1
Issue
1
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
fd49ebcb
编写于
10月 20, 2019
作者:
B
bingyanghuang
提交者:
Tao Luo
10月 20, 2019
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update int8 benchmark with 6271 data, test=develop test=document_fix (#20736)
上级
95e90aa1
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
21 addition
and
21 deletion
+21
-21
paddle/fluid/inference/tests/api/int8_mkldnn_quantization.md
paddle/fluid/inference/tests/api/int8_mkldnn_quantization.md
+14
-14
python/paddle/fluid/contrib/slim/tests/QAT_mkldnn_int8_readme.md
...paddle/fluid/contrib/slim/tests/QAT_mkldnn_int8_readme.md
+7
-7
未找到文件。
paddle/fluid/inference/tests/api/int8_mkldnn_quantization.md
浏览文件 @
fd49ebcb
...
...
@@ -42,25 +42,25 @@ We provide the results of accuracy and performance measured on Intel(R) Xeon(R)
| Model | FP32 Accuracy | INT8 Accuracy | Accuracy Diff(FP32-INT8) |
| :----------: | :-------------: | :------------: | :--------------: |
| GoogleNet | 70.50% |
69.81% | 0.69
% |
| MobileNet-V1 | 70.78% | 70.4
2% | 0.36
% |
| MobileNet-V2 | 71.90% | 71.3
5% | 0.55
% |
| ResNet-101 | 77.50% | 77.4
2% | 0.08
% |
| ResNet-50 | 76.63% | 76.5
2% | 0.11
% |
| VGG16 | 72.08% | 72.0
3% | 0.05
% |
| VGG19 | 72.57% | 72.5
5% | 0.02
% |
| GoogleNet | 70.50% |
70.08% | 0.42
% |
| MobileNet-V1 | 70.78% | 70.4
1% | 0.37
% |
| MobileNet-V2 | 71.90% | 71.3
4% | 0.56
% |
| ResNet-101 | 77.50% | 77.4
3% | 0.07
% |
| ResNet-50 | 76.63% | 76.5
7% | 0.06
% |
| VGG16 | 72.08% | 72.0
5% | 0.03
% |
| VGG19 | 72.57% | 72.5
7% | 0.00
% |
>**II. Throughput on Intel(R) Xeon(R) Gold 6271 (batch size 1 on single core)**
| Model | FP32 Throughput(images/s) | INT8 Throughput(images/s) | Ratio(INT8/FP32)|
| :-----------:| :------------: | :------------: | :------------: |
| GoogleNet | 3
4.06 | 72.79 | 2.14
|
| MobileNet-V1 |
80.02 | 230.65 | 2.88
|
| MobileNet-V2 |
99.38 | 206.92 | 2.08
|
| ResNet-101 | 7.
38 | 27.31 | 3.70
|
| ResNet-50 | 13.
71 | 50.55 | 3.69
|
| VGG16 | 3.
64 | 10.56 | 2.90
|
| VGG19 | 2.
95 | 9.02 | 3.05
|
| GoogleNet | 3
2.76 | 67.43 | 2.06
|
| MobileNet-V1 |
73.96 | 218.82 | 2.96
|
| MobileNet-V2 |
87.94 | 193.70 | 2.20
|
| ResNet-101 | 7.
17 | 26.37 | 3.42
|
| ResNet-50 | 13.
26 | 48.72 | 3.67
|
| VGG16 | 3.
47 | 10.10 | 2.91
|
| VGG19 | 2.
82 | 8.68 | 3.07
|
*
## Prepare dataset
...
...
python/paddle/fluid/contrib/slim/tests/QAT_mkldnn_int8_readme.md
浏览文件 @
fd49ebcb
...
...
@@ -65,12 +65,12 @@ Notes:
| Model | Fake QAT Original Throughput(images/s) | INT8 Throughput(images/s) | Ratio(INT8/FP32)|
| :-----------:| :-------------------------: | :------------: | :------------: |
| MobileNet-V1 | 1
3.66 | 114.98 | 8.42
|
| MobileNet-V2 |
10.22 | 79.78 | 7.81
|
| ResNet101 | 2.
65 | 18.97 | 7.16
|
| ResNet50 | 4.
58 | 35.09 | 7.66
|
| VGG16 | 2.
38 | 9.93 | 4.17
|
| VGG19 |
2.03 | 8.53 | 4.20
|
| MobileNet-V1 | 1
2.86 | 118.05 | 9.18
|
| MobileNet-V2 |
9.76 | 85.89 | 8.80
|
| ResNet101 | 2.
55 | 19.40 | 7.61
|
| ResNet50 | 4.
39 | 35.78 | 8.15
|
| VGG16 | 2.
26 | 9.89 | 4.38
|
| VGG19 |
1.96 | 8.41 | 4.29
|
## 3. How to reproduce the results
Three steps to reproduce the above-mentioned accuracy results, and we take ResNet50 benchmark as an example:
...
...
@@ -95,7 +95,7 @@ cd /PATH/TO/DOWNLOAD/MODEL/
wget http://paddle-inference-dist.bj.bcebos.com/int8/
${
MODEL_FILE_NAME
}
```
To download and
verify all the 7 models, you need to set
`MODEL_NAME`
to one of the following values in command line:
Unzip the downloaded model to the folder.To
verify all the 7 models, you need to set
`MODEL_NAME`
to one of the following values in command line:
```
text
QAT MKL-DNN 1.0
MODEL_NAME=ResNet50, ResNet101, GoogleNet, MobileNetV1, MobileNetV2, VGG16, VGG19
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录