Skip to content

Commit

Permalink
Merge pull request #113 from littletomatodonkey/fix_t4
Browse files Browse the repository at this point in the history
fix mobile pngs
  • Loading branch information
littletomatodonkey committed May 10, 2020
2 parents 75370f7 + d400252 commit b297618
Show file tree
Hide file tree
Showing 3 changed files with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
<img src="./docs/images/models/T4_benchmark/t4.fp32.bs4.main_fps_top1.png" width="700">
</div>

上图对比了一些最新的面向服务器端应用场景的模型,在使用V100,FP32和TensorRT预测一张图像的时间和其准确率,图中准确率82.4%的ResNet50_vd_ssld和83.7%的ResNet101_vd_ssld,是采用PaddleClas提供的SSLD知识蒸馏方案训练的模型。图中相同颜色和符号的点代表同一系列不同规模的模型。不同模型的简介、FLOPS、Parameters以及详细的GPU预测时间请参考文档教程中的[**模型库章节**](https://paddleclas.readthedocs.io/zh_CN/latest/models/models_intro.html)
上图对比了一些最新的面向服务器端应用场景的模型,在使用T4,FP32和TensorRT,batch size为4时的预测时间及其准确率,图中准确率82.4%的ResNet50_vd_ssld和83.7%的ResNet101_vd_ssld,是采用PaddleClas提供的SSLD知识蒸馏方案训练的模型。图中相同颜色和符号的点代表同一系列不同规模的模型。不同模型的简介、FLOPS、Parameters以及详细的GPU预测时间请参考文档教程中的[**模型库章节**](https://paddleclas.readthedocs.io/zh_CN/latest/models/models_intro.html)

<div align="center">
<img
Expand Down
Binary file modified docs/images/models/mobile_arm_storage.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified docs/images/models/mobile_arm_top1.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit b297618

Please sign in to comment.