where is the module named aimet_torch.pro?

[GoldenSpark]

trafficstars

For the file "quantization_aware_training.py" in the folder "Example", aimet_torch.pro module can not be found. How to get this part of source code?

[quic-ssiddego]

Hi @GoldenSpark Thank you for reporting this error. Could you please update the import to "from aimet_torch import quantsim as q" and give it a try.

[fmbao]

In the deepspeech quantize demo code , elif isinstance(op, aimet_torch.pro.qc_quantize_recurrent.QcQuantizeRecurrent): for q_name, input_quantizer in op.input_quantizers.items(): input_quantizer.enabled = mc[q_name + '_quantizer'] for q_name, output_quantizer in op.output_quantizers.items(): output_quantizer.enabled = mc[q_name + '_quantizer'] for q_name, param_quantizer in op.param_quantizers.items(): param_quantizer.enabled = mc[q_name + '_quantizer'] If RNN would like to be quantized, we must use aimet_torch.pro. How to fix this problem.

[fmbao]

@quic-ssiddego

[ralph-bot]

I changed the aimet_torch.pro.quantsim to aimet_torch.quantsim . it look works

[quic-mangal]

Closing this issue due to inactivity. Please re-open it/ create a new issue if you need further help.