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
devil_zzz123
PaddleOCR
提交
4135eb0c
P
PaddleOCR
项目概览
devil_zzz123
/
PaddleOCR
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleOCR
通知
2
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
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
PaddleOCR
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
0
Issue
0
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
4135eb0c
编写于
5月 13, 2021
作者:
T
tink2123
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add qps
上级
cca7cd1e
变更
2
显示空白变更内容
内联
并排
Showing
2 changed file
with
73 addition
and
72 deletion
+73
-72
deploy/pdserving/README.md
deploy/pdserving/README.md
+37
-36
deploy/pdserving/README_CN.md
deploy/pdserving/README_CN.md
+36
-36
未找到文件。
deploy/pdserving/README.md
浏览文件 @
4135eb0c
...
...
@@ -158,42 +158,43 @@ The recognition model is the same.
The predicted performance data will be automatically written into the `PipelineServingLogs/pipeline.tracer` file.
Tested on 200 real pictures, and limited the detection long side to 960. The average QPS on T4 GPU can reach around 13:
```
2021-05-12 10:03:24,812 ==================== TRACER ======================
2021-05-12 10:03:24,904 Op(rec):
2021-05-12 10:03:24,904 in[51.5634921875 ms]
2021-05-12 10:03:24,904 prep[215.310859375 ms]
2021-05-12 10:03:24,904 midp[33.1617109375 ms]
2021-05-12 10:03:24,905 postp[10.451234375 ms]
2021-05-12 10:03:24,905 out[9.736765625 ms]
2021-05-12 10:03:24,905 idle[0.1914292677880819]
2021-05-12 10:03:24,905 Op(det):
2021-05-12 10:03:24,905 in[218.63487096774193 ms]
2021-05-12 10:03:24,906 prep[357.35925 ms]
2021-05-12 10:03:24,906 midp[31.47598387096774 ms]
2021-05-12 10:03:24,906 postp[15.274870967741936 ms]
2021-05-12 10:03:24,906 out[16.245693548387095 ms]
2021-05-12 10:03:24,906 idle[0.3675805857279226]
2021-05-12 10:03:24,906 DAGExecutor:
2021-05-12 10:03:24,906 Query count[128]
2021-05-12 10:03:24,906 QPS[12.8 q/s]
2021-05-12 10:03:24,906 Succ[1.0]
2021-05-12 10:03:24,907 Error req[]
2021-05-12 10:03:24,907 Latency:
2021-05-12 10:03:24,907 ave[798.6557734374998 ms]
2021-05-12 10:03:24,907 .50[867.936 ms]
2021-05-12 10:03:24,907 .60[914.507 ms]
2021-05-12 10:03:24,907 .70[961.064 ms]
2021-05-12 10:03:24,907 .80[1043.264 ms]
2021-05-12 10:03:24,907 .90[1117.923 ms]
2021-05-12 10:03:24,907 .95[1207.056 ms]
2021-05-12 10:03:24,908 .99[1325.008 ms]
2021-05-12 10:03:24,908 Channel (server worker num[10]):
2021-05-12 10:03:24,909 chl0(In: ['@DAGExecutor'], Out: ['det']) size[0/0]
2021-05-12 10:03:24,909 chl1(In: ['det'], Out: ['rec']) size[1/0]
2021-05-12 10:03:24,910 chl2(In: ['rec'], Out: ['@DAGExecutor']) size[0/0]
Tested on 200 real pictures, and limited the detection long side to 960. The average QPS on T4 GPU can reach around 23:
```
2021-05-13 03:42:36,895 ==================== TRACER ======================
2021-05-13 03:42:36,975 Op(rec):
2021-05-13 03:42:36,976 in[14.472382882882883 ms]
2021-05-13 03:42:36,976 prep[9.556855855855856 ms]
2021-05-13 03:42:36,976 midp[59.921905405405404 ms]
2021-05-13 03:42:36,976 postp[15.345945945945946 ms]
2021-05-13 03:42:36,976 out[1.9921216216216215 ms]
2021-05-13 03:42:36,976 idle[0.16254943864471572]
2021-05-13 03:42:36,976 Op(det):
2021-05-13 03:42:36,976 in[315.4468035714286 ms]
2021-05-13 03:42:36,976 prep[69.5980625 ms]
2021-05-13 03:42:36,976 midp[18.989535714285715 ms]
2021-05-13 03:42:36,976 postp[18.857803571428573 ms]
2021-05-13 03:42:36,977 out[3.1337544642857145 ms]
2021-05-13 03:42:36,977 idle[0.7477961159203756]
2021-05-13 03:42:36,977 DAGExecutor:
2021-05-13 03:42:36,977 Query count[224]
2021-05-13 03:42:36,977 QPS[22.4 q/s]
2021-05-13 03:42:36,977 Succ[0.9910714285714286]
2021-05-13 03:42:36,977 Error req[169, 170]
2021-05-13 03:42:36,977 Latency:
2021-05-13 03:42:36,977 ave[535.1678348214285 ms]
2021-05-13 03:42:36,977 .50[172.651 ms]
2021-05-13 03:42:36,977 .60[187.904 ms]
2021-05-13 03:42:36,977 .70[245.675 ms]
2021-05-13 03:42:36,977 .80[526.684 ms]
2021-05-13 03:42:36,977 .90[854.596 ms]
2021-05-13 03:42:36,977 .95[1722.728 ms]
2021-05-13 03:42:36,977 .99[3990.292 ms]
2021-05-13 03:42:36,978 Channel (server worker num[10]):
2021-05-13 03:42:36,978 chl0(In: ['@DAGExecutor'], Out: ['det']) size[0/0]
2021-05-13 03:42:36,979 chl1(In: ['det'], Out: ['rec']) size[6/0]
2021-05-13 03:42:36,979 chl2(In: ['rec'], Out: ['@DAGExecutor']) size[0/0]
```
...
...
deploy/pdserving/README_CN.md
浏览文件 @
4135eb0c
...
...
@@ -155,42 +155,42 @@ python3 -m paddle_serving_client.convert --dirname ./ch_ppocr_mobile_v2.0_rec_in
预测性能数据会被自动写入 `PipelineServingLogs/pipeline.tracer` 文件中。
在200张真实图片上测试,把检测长边限制为960。T4 GPU 上 QPS 均值可达到
1
3左右:
```
2021-05-1
2 10:03:24,812
==================== TRACER ======================
2021-05-1
2 10:03:24,904
Op(rec):
2021-05-1
2 10:03:24,904 in[51.5634921875
ms]
2021-05-1
2 10:03:24,904 prep[215.310859375
ms]
2021-05-1
2 10:03:24,904 midp[33.1617109375
ms]
2021-05-1
2 10:03:24,905 postp[10.451234375
ms]
2021-05-1
2 10:03:24,905 out[9.73676562
5 ms]
2021-05-1
2 10:03:24,905 idle[0.1914292677880819
]
2021-05-1
2 10:03:24,905
Op(det):
2021-05-1
2 10:03:24,905 in[218.63487096774193
ms]
2021-05-1
2 10:03:24,906 prep[357.359
25 ms]
2021-05-1
2 10:03:24,906 midp[31.47598387096774
ms]
2021-05-1
2 10:03:24,906 postp[15.274870967741936
ms]
2021-05-1
2 10:03:24,906 out[16.24569354838709
5 ms]
2021-05-1
2 10:03:24,906 idle[0.367580585727922
6]
2021-05-1
2 10:03:24,906
DAGExecutor:
2021-05-1
2 10:03:24,906 Query count[128
]
2021-05-1
2 10:03:24,906 QPS[12.8
q/s]
2021-05-1
2 10:03:24,906 Succ[1.0
]
2021-05-1
2 10:03:24,907 Error req[
]
2021-05-1
2 10:03:24,90
7 Latency:
2021-05-1
2 10:03:24,907 ave[798.6557734374998
ms]
2021-05-1
2 10:03:24,907 .50[867.936
ms]
2021-05-1
2 10:03:24,907 .60[914.507
ms]
2021-05-1
2 10:03:24,907 .70[961.064
ms]
2021-05-1
2 10:03:24,907 .80[1043.26
4 ms]
2021-05-1
2 10:03:24,907 .90[1117.923
ms]
2021-05-1
2 10:03:24,907 .95[1207.056
ms]
2021-05-1
2 10:03:24,908 .99[1325.008
ms]
2021-05-1
2 10:03:24,90
8 Channel (server worker num[10]):
2021-05-1
2 10:03:24,909
chl0(In: ['@DAGExecutor'], Out: ['det']) size[0/0]
2021-05-1
2 10:03:24,909 chl1(In: ['det'], Out: ['rec']) size[1
/0]
2021-05-1
2 10:03:24,910
chl2(In: ['rec'], Out: ['@DAGExecutor']) size[0/0]
在200张真实图片上测试,把检测长边限制为960。T4 GPU 上 QPS 均值可达到
2
3左右:
```
2021-05-1
3 03:42:36,895
==================== TRACER ======================
2021-05-1
3 03:42:36,975
Op(rec):
2021-05-1
3 03:42:36,976 in[14.472382882882883
ms]
2021-05-1
3 03:42:36,976 prep[9.556855855855856
ms]
2021-05-1
3 03:42:36,976 midp[59.921905405405404
ms]
2021-05-1
3 03:42:36,976 postp[15.345945945945946
ms]
2021-05-1
3 03:42:36,976 out[1.992121621621621
5 ms]
2021-05-1
3 03:42:36,976 idle[0.16254943864471572
]
2021-05-1
3 03:42:36,976
Op(det):
2021-05-1
3 03:42:36,976 in[315.4468035714286
ms]
2021-05-1
3 03:42:36,976 prep[69.59806
25 ms]
2021-05-1
3 03:42:36,976 midp[18.989535714285715
ms]
2021-05-1
3 03:42:36,976 postp[18.857803571428573
ms]
2021-05-1
3 03:42:36,977 out[3.133754464285714
5 ms]
2021-05-1
3 03:42:36,977 idle[0.747796115920375
6]
2021-05-1
3 03:42:36,977
DAGExecutor:
2021-05-1
3 03:42:36,977 Query count[224
]
2021-05-1
3 03:42:36,977 QPS[22.4
q/s]
2021-05-1
3 03:42:36,977 Succ[0.9910714285714286
]
2021-05-1
3 03:42:36,977 Error req[169, 170
]
2021-05-1
3 03:42:36,97
7 Latency:
2021-05-1
3 03:42:36,977 ave[535.1678348214285
ms]
2021-05-1
3 03:42:36,977 .50[172.651
ms]
2021-05-1
3 03:42:36,977 .60[187.904
ms]
2021-05-1
3 03:42:36,977 .70[245.675
ms]
2021-05-1
3 03:42:36,977 .80[526.68
4 ms]
2021-05-1
3 03:42:36,977 .90[854.596
ms]
2021-05-1
3 03:42:36,977 .95[1722.728
ms]
2021-05-1
3 03:42:36,977 .99[3990.292
ms]
2021-05-1
3 03:42:36,97
8 Channel (server worker num[10]):
2021-05-1
3 03:42:36,978
chl0(In: ['@DAGExecutor'], Out: ['det']) size[0/0]
2021-05-1
3 03:42:36,979 chl1(In: ['det'], Out: ['rec']) size[6
/0]
2021-05-1
3 03:42:36,979
chl2(In: ['rec'], Out: ['@DAGExecutor']) size[0/0]
```
...
...
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