Hello KDeni,Dynamic quantization scheme for the activations is not supported. This implied that the quantization parameter are computed during the quantization process, in your case, during the call of the TFLiteInterpreter with the calibration data....
Hello,According the shared code, I think that you have an issue when you initalize the ai_buffer handlers before to call the ai_network_run() function. The passed @ are not correct, "in_data" and "out_data" are the array of pointer, code should be m...
Hello Pietro,Your way to create the npz seems correct. We have perhaps an issue in the associated Cloud service to manage this simple case: input_shape=(1,), investigation is on-going on our side (including the documentation aspect). However, normaly...
Thanks for your data and models (and status). Effectively after analysis, I had detected an issue in cifar10_test_label.npy file where the one shot encoding representation was wrong (left-shift per one in the index). I dont't know if the "MCU_AI-mas...
