search

ai-techsystems / deepC

vendor independent TinyML deep learning library, compiler and inference framework microcomputers and micro-controllers
https://cainvas.ai-tech.systems/
Apache License 2.0
558 stars 86 forks source link

How to embed the weights into the library? #137

Open monkbai opened 3 years ago

monkbai commented 3 years ago

So far the compiled library seems to do not contain weights, is it possible to embed the weights into the binary?

github-actions[bot] commented 3 years ago

Thank you so much for filing the issue. We will look at it and take appropriate action as soon as possible.' first issue

srohit0 commented 3 years ago

weights are part of library and header file.

Can you be more specific on how do you know if the compiled library does not contain weights?

Also, let us know what you find in https://github.com/apache/tvm/issues/7170 ?

monkbai commented 3 years ago

If I follow the steps described in the video you provided and compile the onnx model under the directory with command compile-onnx, it will generate a cpp file and *.weight files, it looks like the weights are read at runtime.

As for tvm, I haven't succeeded to embed weights in binary so far, but they provided some advice, maybe you can follow the discussion here.