aimet_tensorflow.mixed_precision¶
Top-level API for Regular AMP
Top-level API for Fast AMP (AMP 2.0)
Note
To enable phase-3 set the attribute GreedyMixedPrecisionAlgo.ENABLE_CONVERT_OP_REDUCTION = True
Currently only two candidates are supported - ((8,int), (8,int)) & ((16,int), (8,int))
Quantizer Groups definition
CallbackFunc Definition