PaddleOCR/doc/doc_ch/benchmark.md

21 lines
973 B
Markdown
Raw Blame History

This file contains invisible Unicode characters!

This file contains invisible Unicode characters that may be processed differently from what appears below. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to reveal hidden characters.

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# Benchmark
本文给出了PaddleOCR超轻量中文模型8.6M在各平台的预测耗时benchmark。
## 测试数据
- 从中文公开数据集[ICDAR2017-RCTW](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/datasets.md#ICDAR2017-RCTW-17)中随机采样**500**张图像。
该集合大部分图片是通过手机摄像头在野外采集的。有些是截图。这些图片展示了各种各样的场景,包括街景、海报、菜单、室内场景和手机应用程序的截图。
## 评估指标
在四种平台上的预测耗时指标如下:
|长边尺寸(px)|T4(s)|V100(s)|Intel至强6148(s)|骁龙855(s)|
|-|-|-|-|-|
|960|0.092|0.057|0.656|0.354|
|640|0.067|0.045|0.386| 0.236|
|480|0.057|0.043|0.241| 0.175|
说明:
- 评估耗时阶段为图像输入到结果输出的完整阶段,包括了图像的预处理和后处理。
- `Intel至强6148`为服务器端CPU型号。
- `骁龙855`为移动端处理平台型号。