...
Please refer here for the environment construction procedure.
| Info |
|---|
Please note that the following environment settings must be performed every time the CV Tool container is started. |
For ambaCV2X camera
| Code Block |
|---|
$ cd /home/cvtool
$ source setup_env.sh |
For ambaCV5X camera
| Code Block |
|---|
$ cd /home/cvtool
$ source setup_env.sh ipro-ambaCV5X |
Convert sample models
...
You can understand the flow of the conversion process by converting a sample model. If you are converting a model that you have developed, you can skip this step.
mobilenetv2
Move directory.
...
| Code Block |
|---|
(yolov5) $ cd /home/cvtool/conversion/onnx/yolov5 $ ./setup_yolov5.sh (yolov8) $ cd /home/cvtool/conversion/onnx/yolov8 $ ./setup_yolov8.sh |
| Info |
|---|
The file size to be downloaded will be several GB. Please make sure you have enough free space before proceeding. |
Convert the model.
| Code Block |
|---|
$ ./onnx_conversion.sh setting.conf |
| Info |
|---|
Depending on your PC environment, you may need up to 8GB of memory (RAM). If it fails, please check your memory capacity. |
The model after conversion is output to the following directory.
...
${OUTPUT_DIR}/${NET_NAME}_ambaCV5X/${PARSER_OPTION}/[model name]
...
Convert user AI model
...
| Note |
|---|
Pytorch model needs to be converted to ONNX in advance. |
...
Change the parameter of "setting.conf" according to the model to be converted.
Locate user AI model in “MODEL_DIR“ in “setting.conf”.
Convert the model.
| Code Block |
|---|
$ ./onnx_conversion.sh setting.conf |
| Info |
|---|
If an error occurs, please check the environment settings (source setup_env.sh) below. You will need to do this every time you restart your computer. Install AI model convert tool - Technology Partner FAQ (En) - Confluence |
setting.conf
...
| Note |
|---|
From v1.20, parameter "CAVALRY_VER" is removed that existed in setting.conf until v1.19. |
...