sawantkumar
sawantkumar
Hi @mmayers88 , From what i know, i think the libhexagon_nn_skel.so and other ".so" files are provided by Qualcomm itself and is a part of snapdragon SDK instead of tensorflow...
Sorry, i misunderstood the question first time, can you please check this [link](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/delegates/hexagon/hexagon_nn) and let me know if this is the one you are looking for .
Hi. @pkgoogle , Can you please suggest, which one of the above two commands will be able to build the gpu delegate ?
Hi @perphyguo , I cloned the https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/android and was able to build the project with the android with the "Android Gradle Plugin version =72.1" and "gradle version = 7.3.3" ....
Hi @perphyguo , Can you please let me know if the provided solution worked for you?
Hi @gustavla , I am in the process of replicating your issue . I will get back to you as soon as poosible.
Hi @gustavla , I replicated your issue and i got the same result as yours . I will try to replicate the issue through an android app and will let...
Hi @gustavla , Can you please reproduce this error through an Android app please and let me know? That way it will be easier for me to debug the issue.
Hi @gustavla , Usually its either images or video data which I use as input . But here i need to create .npy files or put the inputs in a...
Hi @pkgoogle , I replicated his code and the converted model size comes out to be of 500kb . Can you please take a look?