From fa8e88e091d19bcb05e4c34c2fae92f87990ce9d Mon Sep 17 00:00:00 2001 From: shangliang Xu Date: Mon, 10 Oct 2022 17:50:24 +0800 Subject: [PATCH] [docs] add ppyoloe e2e speed docs, test=document_fix (#7018) (#7085) --- configs/ppyoloe/README.md | 10 +++++++++- configs/ppyoloe/README_cn.md | 9 +++++++++ 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/configs/ppyoloe/README.md b/configs/ppyoloe/README.md index 5b29a91b9..f144b1c5f 100644 --- a/configs/ppyoloe/README.md +++ b/configs/ppyoloe/README.md @@ -50,6 +50,14 @@ PP-YOLOE is composed of following methods: | PP-YOLOE+_x | 80 | 54.7 | 72.0 | 59.9 | 37.9 | 59.3 | 70.4 | 57.0 | 78.7 | 87.2 | +### End-to-end Speed +| Model | AP0.5:0.95 | TRT-FP32(fps) | TRT-FP16(fps) | +|:-----------:|:---------------:|:-------------:|:-------------:| +| PP-YOLOE+_s | 43.7 | 44.44 | 47.85 | +| PP-YOLOE+_m | 49.8 | 39.06 | 43.86 | +| PP-YOLOE+_l | 52.9 | 34.01 | 42.02 | +| PP-YOLOE+_x | 54.7 | 26.88 | 36.76 | + **Notes:** - PP-YOLOE is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset. @@ -58,7 +66,7 @@ PP-YOLOE is composed of following methods: - PP-YOLOE inference speed is tesed on single Tesla V100 with batch size as 1, **CUDA 10.2**, **CUDNN 7.6.5**, **TensorRT 6.0.1.8** in TensorRT mode. - Refer to [Speed testing](#Speed-testing) to reproduce the speed testing results of PP-YOLOE. - If you set `--run_benchmark=True`，you should install these dependencies at first, `pip install pynvml psutil GPUtil`. - +- End-to-end speed test includes pre-processing + inference + post-processing and NMS time, using **Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz**, **single Tesla V100**, **CUDA 11.2**, **CUDNN 8.2.0**, **TensorRT 8.0.1.6**. ### Feature Models diff --git a/configs/ppyoloe/README_cn.md b/configs/ppyoloe/README_cn.md index e9acb7980..42a9b6e05 100644 --- a/configs/ppyoloe/README_cn.md +++ b/configs/ppyoloe/README_cn.md @@ -50,6 +50,14 @@ PP-YOLOE由以下方法组成 | PP-YOLOE+_x | 80 | 54.7 | 72.0 | 59.9 | 37.9 | 59.3 | 70.4 | 57.0 | 78.7 | 87.2 | +### 端到端速度 +| 模型 | AP0.5:0.95 | TRT-FP32(fps) | TRT-FP16(fps) | +|:------------------------:|:---------------:|:-------------:|:-------------:| +| PP-YOLOE+_s | 43.7 | 44.44 | 47.85 | +| PP-YOLOE+_m | 49.8 | 39.06 | 43.86 | +| PP-YOLOE+_l | 52.9 | 34.01 | 42.02 | +| PP-YOLOE+_x | 54.7 | 26.88 | 36.76 | + **注意:** - PP-YOLOE模型使用COCO数据集中train2017作为训练集，使用val2017和test-dev2017作为测试集。 @@ -58,6 +66,7 @@ PP-YOLOE由以下方法组成 - PP-YOLOE模型推理速度测试采用单卡V100，batch size=1进行测试，使用**CUDA 10.2**, **CUDNN 7.6.5**，TensorRT推理速度测试使用**TensorRT 6.0.1.8**。 - 参考[速度测试](#速度测试)以复现PP-YOLOE推理速度测试结果。 - 如果你设置了`--run_benchmark=True`, 你首先需要安装以下依赖`pip install pynvml psutil GPUtil`。 +- 端到端速度测试包含模型前处理 + 模型推理 + 模型后处理及NMS的时间，测试使用**Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz**, **单卡V100**, **CUDA 11.2**, **CUDNN 8.2.0**, **TensorRT 8.0.1.6**。 ### 垂类应用模型 -- GitLab