I am looking for someway of using the armNN SDK on a Xilinx Zynq Platform which has Quad-core ARM® CortexTM-A53 MPCoreTM up to 1.5GHz and an ARM MALI 400 MP2 GPU. With ARM Mali GPU noted off in a previous question my next task is to look into if it is possible to run the SDK on the Cortex processor but lloking at the guides I would only be able to cross compile it. So my first question is that is it possible to run it on the ARM A53 on the Zynq Platform and also if tensorflow would run on it as well.
You can run the Arn NN software on the Xilinx platform. You can compile it on the board or cross-compile it on another machine and copy to the board.
Since you cannot use OpenCL with this Mali GPU you can configure to disable the OpenCL support and just use the optimized Neon support for the Cortex-A53 CPUs.
An example of how to compile it on a similar board running Linux can be found at: https://github.com/ARM-software/Tool-Solutions/tree/master/ml-tool-examples/build-armnn
There are some more examples of how to build listed at: https://developer.arm.com/technologies/machine-learning-on-arm/developer-material/how-to-guides
If you want to do performance analysis of your application we also have Streamline for Arm NN. There is an example of how to use it at: https://github.com/ARM-software/Tool-Solutions/tree/master/ml-tool-examples/mnist-demo This is a nice demonstration of the entire process.
Please feel free to let me know if you are trying to native compile on the Xilinx board or you want to cross-compile and I can outline the process for you. Native compile takes a little longer, but is actually easier.
Is your Xilinx board running Linux? Which distribution?