armnn

armnn copied to clipboard

compilation error: `array subscript 5 is above array bounds` with `aarch64-none-linux-gnu-g++ 12.2.Rel1`

2

I'm trying to cross compile ArmNN with Arm Compute Library backend using the Arm GNU Toolchain 12.2.Rel1 and this compilation error occurs : ``` In file included from /home/mcoutant/work/armnn/include/armnn/Types.hpp:7, from...

maxmarsc

Crash when support ArmNN AIDL backend based on a shim over the NNAPI Support Library

2

Hello team, On v23.02, I was trying to support ArmNN AIDL based on a shim over the NNAPI Support Library. Step: 1. In device.mk, add: PRODUCT_PACKAGES += android.hardware.neuralnetworks-shim-service-armnn 2. In...

Cherry-Android

Does ExecuteNetwork support "GpuAcc" runtime ?

12

Hello Team, I am trying to execute a NeuralNetwork in my custom developed SoC in a emulation platform (ZEBU). I have Mali G710 Gpu integrated with Cortex Arm53 CPU. I...

somasundaram1702

Running YOLOv5 ONNX model with onnx parser of armnn fails with unsupported operation

2

Traceback (most recent call last): File "/home/sl-rpi-5/Downloads/armnn/python/pyarmnn/examples/object_detection/yolov5_onnx_parser.py", line 114, in main(args) File "/home/sl-rpi-5/Downloads/armnn/python/pyarmnn/examples/object_detection/yolov5_onnx_parser.py", line 55, in main executor = NetworkExecutor(*exec_input_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/sl-rpi-5/Downloads/armnn/python/pyarmnn/examples/object_detection/network_executor.py", line 22, in __init__ self.network_id, self.runtime, self.input_binding_info,...

Murari007

Profiler service warnings seen in ArmNN v24.02

3

Hi, On ArmNN v24.02, I am currently seeing the below profiler warnings when using ExecuteNetwork from the pre-built ArmNN binaries found in the release assets: ``` ~/armnn-prebuilt-2402# LD_LIBRARY_PATH=. ./ExecuteNetwork -c...

aymanchaudhry

Unsupported Operation "Transpose" in armNN::OnnxParser while loading the onnx model file (in the goal to run inference)

8

Hi, There are two operators which are main concern that I am raising as an issue here. "Transpose" and "ConvTranspose". Currently I am using an Onnx file to parse the...

pandianAK

nvalid attempt to construct ConstTensor from non-constant TensorInfo

1

os:ubuntu 18.04 model formate：tflite Anybody help me？  

tianyashu2020

Another error on another model and by now it's two out of three :(

22

[feather_lite.zip](https://github.com/ARM-software/armnn/files/14824271/feather_lite.zip) any of the three versions of this very simple model (that enlightens images) works fine with the default interpreter but fail with the armnn delegate (last version) with error:...

federicoparra

Build Issues -Werrors on armbian 24

1

I'm trying to build your software on Armbian 24.2.1 with the following versions: gcc (Debian 12.2.0-14) 12.2.0 cmake version 3.29.0 Armbian 24.2.1 bookworm I am using the following build command...

ChthonicOne

understanding the onnx parser

2

Hi, I am currently trying to understand the ONNX parser. Is there any developer documentation or any other resources available that can help me understand the parser quickly, or do...

kumarutkarsh1248