ZF/insightface
1
0
Fork 0
mirror of https://github.com/deepinsight/insightface.git synced 2025-12-30 08:02:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

update README.md

Browse Source
This commit is contained in:
GuoxiaWang
2021-10-14 10:55:34 +08:00
parent 05e9748ec5
commit 0c8f81369d
3 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
detection/blazeface_paddle/README_ch.md → detection/blazeface_paddle/README_cn.md
View File

@@ -22,7 +22,7 @@
`Arcface-Paddle`是基于PaddlePaddle实现的，开源深度人脸检测、识别工具。`Arcface-Paddle`目前提供了三个预训练模型，包括用于人脸检测的 `BlazeFace`、用于人脸识别的 `ArcFace` 和 `MobileFace`。
- 本部分内容为人脸检测部分，基于PaddleDetection进行开发。
- 人脸识别相关内容可以参考：[人脸识别](../../recognition/arcface_paddle/README_ch.md)。
- 人脸识别相关内容可以参考：[人脸识别](../../recognition/arcface_paddle/README_cn.md)。
- 基于PaddleInference的Whl包预测部署内容可以参考：[Whl包预测部署](https://github.com/littletomatodonkey/insight-face-paddle)。

2
detection/blazeface_paddle/README_en.md
View File

@@ -1,4 +1,4 @@
[简体中文](README_ch.md) | English
[简体中文](README_cn.md) | English
# FaceDetection

14
recognition/arcface_paddle/README.md
View File

@@ -1,4 +1,4 @@
[简体中文](README_ch.md) | English
[简体中文](README_cn.md) | English
# Arcface-Paddle
@@ -179,16 +179,16 @@ sh scripts/inference.sh
### 8.3 Maximum Number of Identities
**Configuration：**
* GPU: 8 NVIDIA Tesla V100 32G
* GPU: 8 NVIDIA Tesla V100 32G (32510MiB)
* BatchSize: 64/512
* SampleRatio: 0.1
| Mode | Precision | Res50 | Res100 |
| Mode | Precision | Res50 | Res100 |
| ------------------------- | --------- | -------- | -------- |
| Framework1 (static) | AMP | 42000000 | 39000000 |
| Framework2 (dynamic) | AMP | 30000000 | 29000000 |
| Paddle (static) | Pure FP16 | 60000000 | 60000000 |
| Paddle (dynamic) | Pure FP16 | 59000000 | 59000000 |
| Framework1 (static) | AMP | 42000000 (31792MiB)| 39000000 (31938MiB)|
| Framework2 (dynamic) | AMP | 30000000 (31702MiB)| 29000000 (32286MiB)|
| Paddle (static) | Pure FP16 | 60000000 (32018MiB)| 60000000 (32018MiB)|
| Paddle (dynamic) | Pure FP16 | 59000000 (31970MiB)| 59000000 (31970MiB)|
**Note:** config environment variable ``export FLAGS_allocator_strategy=naive_best_fit``