Differences

This shows you the differences between two versions of the page.

--- products:sbc:vim4:npu:demos:retinaface [2023/09/18 01:29]
sravan [Convert]
+++ products:sbc:vim4:npu:demos:retinaface [2024/01/29 02:16] (current)
louis
@@ Line 1: / Line 1: @@
-~~tag> NPU Retinaface VIM4 Pytorch~~
+~~tag> NPU RetinaFace VIM4 PyTorch~~
-====== Retinaface Pytorch VIM4 Demo - 5 ======
+====== RetinaFace PyTorch VIM4 Demo - 5 ======
 {{indexmenu_n>5}}
 ===== Get source code =====
+[[gh>bubbliiiing/retinaface-pytorch]]
 ```shell
@@ Line 32: / Line 34: @@
 Follow Docker official documentation to install Docker: [[https://docs.docker.com/engine/install/ubuntu/|Install Docker Engine on Ubuntu]].
-Then fetch the prebuilt NPU Docker Container and run it.
+Then fetch the prebuilt NPU Docker container and run it.
 ```shell
@@ Line 52: / Line 54: @@
 ==== Convert ====
-After training the model, we should convert the Pytorch model to ONNX model. Create the python conversion script as follows and run.
+After training the model, we should convert the PyTorch model into an ONNX model. Create the Python conversion script as follows and run.
 ```python export.py
@@ Line 98: / Line 100: @@
 ```
-Run ''convert_adla.sh'' to generate VIM4 model. The converted model is ''xxx.adla'' in ''onnx_output''.
+Run ''convert_adla.sh'' to generate the VIM4 model. The converted model is ''xxx.adla'' in ''onnx_output''.
 ```shell
@@ Line 152: / Line 154: @@
 # Run
-$ sudo ./retinaface_cap -m ../data/retinaface_int8.adla -d 0 -w 1920 -h 1080
+$ sudo ./retinaface_cap -m ../data/retinaface_int8.adla -d 0
 ```
-''0'' is camera device index.
+''0'' is the camera device index.

Khadas Docs

User Tools

Site Tools

Differences

Page Tools