...
Table of Contents | ||||
---|---|---|---|---|
|
Preparation
...
Please refer here for the environment construction procedure.
...
AI model convert tool: Tensorflow
AI model convert: ONNX(PyTorch)
Evaluate AI model
The CV tool does not include a mechanism to evaluate the inference time, accuracy, etc. of the converted model.
...
Run Please evaluate in one of the following ways.
Running the converted model on the i-PRO camera
...
Inference time
Measure the time before and after the inference execution API (Adam_AI_RunNet()) call
...
Precision
Evaluate the accuracy using the data obtained by the API
...
(Adam_AI_GetOutput()) that acquires the data of the output layer of the model.
...
Using sample app
The CV tool includes a sample app that allows you to obtain inference time and output layer data for the converted model. This page explains how to use it.Using simulator in CV tool
It is possible to perform inference for the converted model. Please refer here on how to use it.
Sample app for evaluation
...
Preparing for the evaluation
...
For details on how to install, refer to the document "AdamAppDevelopmentManualForIpro.pdf" included with the SDK. here.
Also, make sure you have an i-PRO network camera that the app can install on.
...
First, copy the DnnSdApp package (DnnSdApp_V0_45_ambaCV2XambaCV2X5X.ext) in the container to the host PC.
...
Code Block |
---|
$ cd [Work Directory] $ sudo docker run -it --rm -v $(pwd):/work [image name] /bin/bash $ cp /home/cvtool/app/DnnSdApp_V0_45_ambaCV2XambaCV2X5X.ext /work |
Launch a browser and access the detailed setting
...
layernameout: Output layer name (separated by comma for multiple settings)
Note |
---|
DnnSdApp may not work properly, when “/” is contained in layernamein or layernameout. |
NETNAME: Model name
TftpServerIP:TFTP server address where models are stored
*Set if SD card is not used
ChannelNum:Channels of model
ImgHeight:Height of input image
ImgWidth:Width of input image
PixelFormat:Pixel format of model
Prepare evaluation images
...
Code Block |
---|
tar cvzf dnn.tar.gz dnn |
Folder configuration | Remarks | ||
---|---|---|---|
dnn/ | test_jpeg/ | yyy1.jpg | jpeg placement directory, file names are arbitrary File extension: ".jpg", ".jpeg", ".JPG", ".JPEG"
|
yyy2.jpg | |||
: | |||
test_mp4/
| zzz1.mp4 | mp4 placement directory, file name to be deployed is arbitrary File ectension: ".mp4" | |
zzz2.mp4 | |||
: |
Upload images to DnnSdApp
...