Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

In developing additional application with AI, trained AI model on Caffe/Tensorflow/ONNX framework is needed needs to be convert to binary file (cavalry.bin), which is executable executed by accelerator H/W (CVFlow) inside embedded to AI camera.

The CV tool is what does processes this conversion process.

...

Note
  • The target users of this document are supposed to have skill of training AI model.

  • The cvtool is not the tool for training AI model.
    Users have to train it in each framework previouslyin advance.

  • The cvtool handles CNN as target AI model.

  • The model of tensorflow v2.x needs to be converted to tflite in advance.

  • Pytorch model needs to be converted to ONNX in advance

...

The CV Tool handles colored items in the figure below.

...

Retraining of a model is not included in this process.

...

  • only 16bit

  • 16bit/8bit mixed (the CV tool decides data length of each operation)

  • only 8bit

The inference time of 8bit operation results in faster inference time and less accuracy than 16bitis faster but less accurate compared to 16bit operation.

Preparation

...

Please refer here for the environment construction procedure.

...

Please refer to the following page pages for model conversion.

 AI model convert tool: Caffe

...

  • This tool provides the features for developing additional application which is executed in security cameracameras. The behavior of developed application is not guaranteed. In addition, the embedded existing features are will not be guaranteed after installing additional application to the camera.

  • The provided sample files are designed only to instruct show users how to use this tool . They and that they are not developed practically used for the purpose of actual surveillance system.

  • In not no event shall i-PRO Co., Ltd. be liable to any party or any person, except for replacement or reasonable maintenance of the product, for the cases, including but not limited to below;

    • Any damage and loss, including without limitation, direct or indirect, special, consequential or exemplary, arising out of or relating to the product;

    • Personal injury or any damage caused by inappropriate use or neglect operation of the user;

    • Any problems, consequential inconvenience, or loss or damage, arising out of the reverse compiling or reverse engineering of the product;

    • Any loss or damage, or claims arising out from loss or leak of PS data including video data in the PC;

    • Any claim or action for damages, brought by any person or organization being a photogenic subject, due to violation of privacy with the result of that surveillance camera's picture, including saved data, for some reason, becomes public or is used for the purpose other than surveillance;