Jetson-Nano-Ubuntu-20-image VS netron

Or use the Image: https://github.com/Qengineering/Jetson-Nano-Ubuntu-20-image

manually upgrade your 18.04 you installed from flashing jetpack 4.6 following this guide, https://qengineering.eu/install-ubuntu-20.04-on-jetson-nano.html

Hey so I followed the steps here: https://qengineering.eu/install-ubuntu-20.04-on-jetson-nano.html

They're data-dependence graphs for a neural-network scheduling problem. Like this but way bigger to start with and then lowered to more detailed representations several times: https://netron.app/?url=https://github.com/onnx/models/raw/m... My home-grown layout engine can handle the 12k nodes for llama2 in its highest-level form in 20s or so, but its not the most featureful, and they only get bigger from there. So I always have an eye out for potential tools.

Netron seems to be the best that I've seen so far. https://github.com/lutzroeder/netron

In exploring open-source projects, I've come across several promising tools capable of managing deep-learning models for images. Significantly, tools such as NETRON provide visualization of neural networks, while SHAP can be used for evaluating the significance of outputs.

We need to find out the exact input and output tensor names. A tool like Netron makes this super easy. Open the original .tflite and/or the ONNX model in Netron and click the Model Properties button in the lower left corner.

How is this different from e.g Netron https://github.com/lutzroeder/netron

Netron (https://netron.app/) is the best and mostly used NN visualizer. Just save your model and then simply load it via netron to look its layers and weights. If you want a more complex visualization then you can also play with Zetane ( but its paid, also have a free version) engine.