Update the benchmark for apple devices

This commit is contained in:
JingyuYan
2024-08-18 18:11:55 +08:00
parent d1ac587dfc
commit b2646d9040
2 changed files with 19 additions and 0 deletions

View File

@@ -13,6 +13,8 @@ Please contact [contact@insightface.ai](mailto:contact@insightface.ai?subject=In
## Change Logs
**`2024-08-18`** Updating [Benchmark](doc/Benchmark-Remark(Updating).md): Using CoreML with Apple's Neural Engine (ANE) on the iPhone 13, the combined processes of **Face Detection** + **Alignment** + **Feature Extraction** take less than **2ms**.
**`2024-07-17`** Add global resource statistics monitoring to prevent memory leaks.
**`2024-07-07`** Add some face action detection to the face interaction module.

View File

@@ -1,6 +1,23 @@
# Benchmark Remark(Updating)
The benchmark tests will be continuously updated.
## Megatron_Apple(ANE, Apple Neural Engine)
### Device: iPhone13, Apple A15
| **Benchmark** | **Loops** | **Total Time** | **Average Time** |
| ---------------------- | --------- | -------------- | ---------------- |
| Face Detect@160 | 1000 | 711 ms | **0.71 ms** |
| Face Detect@192 | 1000 | 832ms | **0.83ms** |
| Face Detect@256 | 1000 | 931ms | **0.92ms** |
| Face Detect@320 | 1000 | 1324ms | **1.32ms** |
| Face Detect@640 | 1000 | 3881ms | **3.88ms** |
| Face Extract(**MNet**) | 1000 | 853ms | **0.85ms** |
| Face Extract(**R50**) | 1000 | 3856ms | **3.86ms** |
**Note: **The above data inference backend uses CoreML.
## Pikachu
### Device: Macbook pro 16-inch, 2019 2.6 GHz Intel Core i7
| **Benchmark** | **Loops** | **Total Time** | **Average Time** |