I use edge impulse for my project, it should recognize tomatoes on raspberry py, and I need that when raspberry pi sees a tomato, it will send a signal to the Arduino, but how can this be done if edge impulse can only be launched on the command line.
You do not need to use the command line for Edge Impulse. There are a number of ways to run your ML model on a Raspberry Pi, including a C++ library, Python, Go, and Node.js libraries, WebAssembly, and Docker container.
sorry, but i couldn’t find on the internet hot to run it in python or c++m can you tall me or give a link how to do this
I linked to each of the tutorials in my comment above. For C++, I recommend As a generic C++ library - Edge Impulse Documentation
For Python: Linux Python SDK - Edge Impulse Documentation
Sorry, but I didn’t understand how to run image recognition on it and read the data in it
Here is an example of how to capture an image from a webcam on the Raspberry Pi and then run inference to classify that image using the Edge Impulse Python library: https://github.com/edgeimpulse/linux-sdk-python/blob/master/examples/image/classify.py