Hello,
I am using the last PROCESSOR-SDK-J721S2 version ( 8.6.1 ) , and i am trying to import CNN TFLITE models pre-quantized using TIDL OSRT .
With this version of SDK , and on this family of chip ( J721S2 ) , the TIDL roadmap states that it is possible to import pre-quantized TFLITE models ( i quote "TFLite pre quantized model
support with asymmetric quantization" )
Am I correct to assume that this means : import without prior dequantization and then re-calibration, but directly using the int8 weights "as is". ?
I don't know how to enable this feature with the current TIDL parameters , as described in this doc https://github.com/TexasInstruments/edgeai-tidl-tools/blob/master/examples/osrt_python/README.md#basic-options
Please note i am using TIDL OSRT API from Python.
Can you help me to enable this feature and check it works ?
Thank you.