tensorplay.ao.quantization.default_qconfig

tensorplay.ao.quantization.default_qconfig = (MinMaxObserver(quant_min=0, quant_max=127), MinMaxObserver(dtype=tensorplay.int8, quant_min=-128, quant_max=127))

observer factories for activations and weights.

Both fields must be observer classes or callables returning observer instances. Use MyObserver.with_args(x=1) to override constructor arguments.

Type:

Describes how to quantize a layer