Skip to content

P
PaddleOCR

weixin_41840029 / PaddleOCR
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleOCR

通知 1
Star 1
Fork 0
P
PaddleOCR
提交 4135eb0c 编写于 作者: T tink2123
浏览文件
操作

add qps

上级 cca7cd1e
隐藏空白更改
内联 并排
Showing with 73 addition and 72 deletion
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13左右：
```
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]
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23左右：
```
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]
```
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或