User Tools
products:sbc:vim4:npu:demos:facenet
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
products:sbc:vim4:npu:demos:facenet [2024/10/28 21:12] louis |
products:sbc:vim4:npu:demos:facenet [2026/04/02 02:47] (current) nick |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ~~tag> NPU FaceNet VIM4 PyTorch~~ | ~~tag> NPU FaceNet VIM4 PyTorch~~ | ||
| + | |||
| + | **Doc for version ddk-3.4.7.7** | ||
| + | |||
| ====== FaceNet PyTorch VIM4 Demo - 6 ====== | ====== FaceNet PyTorch VIM4 Demo - 6 ====== | ||
| {{indexmenu_n> | {{indexmenu_n> | ||
| + | |||
| + | ===== Introduction ===== | ||
| + | |||
| + | FaceNet is a face recognition model. It will convert a face image into a feature map. Compare the feature map between image and face database. Here are two judgment indicators, cosine similarity and Euclidean distance. The closer the cosine similarity is to 1 and the closer the Euclidean distance is to 0, the more similar is between two faces. | ||
| + | |||
| + | Here takes **lin_1.jpg** as example. Inference results on VIM4. | ||
| + | |||
| + | {{: | ||
| + | |||
| ===== Get Source Code ===== | ===== Get Source Code ===== | ||
| Line 23: | Line 35: | ||
| ``` | ``` | ||
| - | ===== Get Convert Tool ===== | + | ==== Get Convert Tool ==== |
| + | |||
| + | You can find the SDK here: [[dl> | ||
| ```shell | ```shell | ||
| - | $ git lfs install | + | $ wget https://dl.khadas.com/products/ |
| - | $ git lfs clone https://gitlab.com/khadas/ | + | $ tar xvzf vim4_npu_sdk-ddk-3.4.7.7-250508.tgz |
| - | $ cd vim4_npu_sdk | + | $ cd vim4_npu_sdk-ddk-3.4.7.7-250508 |
| $ ls | $ ls | ||
| - | adla-toolkit-binary | + | adla-toolkit-binary |
| ``` | ``` | ||
| - | * '' | + | * '' |
| * '' | * '' | ||
| * '' | * '' | ||
| + | * '' | ||
| - | ==== Get conversion tool ==== | + | <WRAP important> |
| + | If your kernel is older than 241129, please use branch npu-ddk-1.7.5.5. | ||
| + | </ | ||
| - | Download Tool from [[gl> | + | ==== Convert ==== |
| - | + | ||
| - | ```shell | + | |
| - | $ git clone https:// | + | |
| - | ``` | + | |
| After training model, modify '' | After training model, modify '' | ||
| Line 98: | Line 111: | ||
| --dtypes " | --dtypes " | ||
| --inference-input-type float32 \ | --inference-input-type float32 \ | ||
| - | --inference-output-type float32 \ | + | --inference-output-type float32 \ |
| --quantize-dtype int8 --outdir onnx_output | --quantize-dtype int8 --outdir onnx_output | ||
| --channel-mean-value " | --channel-mean-value " | ||
| Line 122: | Line 135: | ||
| $ git clone https:// | $ git clone https:// | ||
| ``` | ``` | ||
| + | |||
| + | <WRAP important> | ||
| + | If your kernel is older than 241129, please use version before tag ddk-3.4.7.7. | ||
| + | </ | ||
| ==== Install dependencies ==== | ==== Install dependencies ==== | ||
| Line 147: | Line 164: | ||
| # Run mode 1 | # Run mode 1 | ||
| - | $ sudo ./facenet -m ../ | + | $ ./facenet -m ../ |
| ``` | ``` | ||
| Line 154: | Line 171: | ||
| ```shell | ```shell | ||
| # Run mode 2 | # Run mode 2 | ||
| - | $ sudo ./facenet -m ../ | + | $ ./facenet -m ../ |
| ``` | ``` | ||
| + | Here are two comparison methods, **Euclidean distance** and **cosine similarity**. | ||
| + | |||
| + | **Euclidean distance** is smaller, more similar between two faces. | ||
| + | |||
| + | **Cosine similarity** is closer to 1, more similar between two faces. | ||
Last modified: 2024/10/28 21:12 by louis