Open answerdon opened 3 weeks ago
Hello answerdon
There are many factors that will effect the execution time and there will be cases where Arm NN does not provide improved performance. Can I suggest you try using the evaluate_network.sh script in armnn/tests/ExecuteNetwork/. This will try different parameters with ExecuteNetwork and the TfLite delegate to help you choose parameters that might improve performance.
Colm.
I have experimented multiple models with ARM-NN on Cortex A53(mostly int8 quantized models with latency < 200ms). And I found XNNPACK generally gives a better latency result than ARM-NN. So I am trying to understand what kind of model can perform better with ARM-NN.
For example, I compared the results using the mobilenet model downloaded from ARMNN model zoo: https://github.com/ARM-software/ML-zoo/tree/master/models/image_classification/mobilenet_v2_1.0_224/tflite_int8