Quantizer

Quantize your network

---

source

Quantizer

 Quantizer (activation_observer=<class
            'torch.ao.quantization.observer.MinMaxObserver'>,
            weight_observer=<class
            'torch.ao.quantization.observer.MinMaxObserver'>,
            activation_qtype=torch.qint8, weight_qtype=torch.quint8,
            granularity='tensor')

Initialize self. See help(type(self)) for accurate signature.